Search

Our study introduces ResNet-L2 (RL2), a novel metric for evaluating generative models and image quality in histopathology, addressing limitations of traditional metrics, such as Frechet inception distance (FID), when the data is scarce. RL2 leverages ResNet features with a normalizing flow to calculate RMSE distance in the latent space, providing reliable assessments across diverse histopathology datasets. We evaluated the performance of RL2 on degradation types, such as blur, Gaussian noise, salt-and-pepper noise, and rectangular patches, as well as diffusion processes. RL2's monotonic response to increasing degradation makes it well-suited for models that assess image quality, proving a valuable advancement for evaluating image generation techniques in histopathology. It can also be used to discard low-quality patches while sampling from a whole slide image. It is also significantly lighter and faster compared to traditional metrics and requires fewer images to give stable metric value., Comment: 7 pages, 5 figures

The crucial role of convolutional models, both as standalone vision models and backbones in foundation models, necessitates effective acceleration techniques. This paper proposes a novel method to learn semi-structured sparsity patterns for convolution kernels in the form of maskings enabling the utilization of readily available hardware accelerations. The approach accelerates convolutional models more than two-fold during inference without decreasing model performance. At the same time, the original model weights and structure remain unchanged keeping the model thus easily updatable. Beyond the immediate practical use, the effect of maskings on prediction is easily quantifiable. Therefore, guarantees on model predictions under maskings are derived showing stability bounds for learned maskings even after updating the original underlying model., Comment: 15 pages, 3 figures; this work will be presented at the NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML)

This paper introduces to a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks, specifically addressing a vowel phonemes classification case study within the Automatic Speech Recognition research field. Through pseudo-Neural Architecture Search and Hyper-Parameters Tuning experiments conducted with an informed grid-search methodology, we achieve classification accuracy comparable to nowadays complex architectures (90.0 - 93.7%). Despite its simplicity, our model prioritizes generalization of language context and distributed applicability, supported by relevant statistical and performance metrics. The experiments code is openly available at our GitHub., Comment: Accepted at "2024 29th IEEE Symposium on Computers and Communications (ISCC): workshop on Next-Generation Multimedia Services at the Edge: Leveraging 5G and Beyond (NGMSE2024)". arXiv admin note: text overlap with arXiv:2410.04098

This paper explores a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks, focusing on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition (ASR) domain. For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets. We formalize combinations of pseudo-Neural Architecture Search and Hyper-Parameters Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures, delving into the speaker recognition and energy efficiency aspects. Despite its simplicity, our model proposal has a very good chance to generalize the language and speaker genders context for widespread applicability in computational constrained contexts, proved by relevant statistical and performance metrics. Our experiments code is openly accessible on our GitHub., Comment: Accepted at "IEEE 5th International Symposium on the Internet of Sounds, 30 Sep / 2 Oct 2024, Erlangen, Germany"

Object detection is a main task in computer vision. Template matching is the reference method for detecting objects with arbitrary templates. However, template matching computational complexity depends on the rotation accuracy, being a limiting factor for large 3D images (tomograms). Here, we implement a new algorithm called tensorial template matching, based on a mathematical framework that represents all rotations of a template with a tensor field. Contrary to standard template matching, the computational complexity of the presented algorithm is independent of the rotation accuracy. Using both, synthetic and real data from tomography, we demonstrate that tensorial template matching is much faster than template matching and has the potential to improve its accuracy, Comment: Accepted in The 18th European Conference on Computer Vision ECCV 2024

The paper presents the second part of a precise description of the prototype that has been developed in the course of the ISAC project over the last two decades. This part describes the "specify-phase", while the first part describing the "solve-phase" is already published. In the specify-phase a student interactively constructs a formal specification. The ISAC prototype implements formal specifications as established in theoretical computer science, however, the input language for the construction avoids requiring users to have knowledge of logic; this makes the system useful for various engineering faculties (and also for high school). The paper discusses not only ISAC's design of the specify-phase in detail, but also gives a brief introduction to implementation with the aim of advertising the re-use of formal frameworks (inclusive respective front-ends) with their generic tools for language definition and their rich pool of software components for formal mathematics., Comment: In Proceedings ThEdu'23, arXiv:2404.03709

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide interpreted results. Such a models often learn to predict the distribution over class labels using additional description of this target instances, called concepts. However, existing Bottleneck methods have a number of limitations: their accuracy is lower than that of a standard model and CBMs require an additional set of concepts to leverage. We provide a framework for creating Concept Bottleneck Model from pre-trained multi-modal encoder and new CLIP-like architectures. By introducing a new type of layers known as Concept Bottleneck Layers, we outline three methods for training them: with $\ell_1$-loss, contrastive loss and loss function based on Gumbel-Softmax distribution (Sparse-CBM), while final FC layer is still trained with Cross-Entropy. We show a significant increase in accuracy using sparse hidden layers in CLIP-based bottleneck models. Which means that sparse representation of concepts activation vector is meaningful in Concept Bottleneck Models. Moreover, with our Concept Matrix Search algorithm we can improve CLIP predictions on complex datasets without any additional training or fine-tuning. The code is available at: https://github.com/Andron00e/SparseCBM., Comment: 23 pages, 1 algorithm, 36 figures

Humans have good natural intuition to recognize when another person has something to say. It would be interesting if an AI can also recognize intentions to speak. Especially in scenarios when an AI is guiding a group discussion, this can be a useful skill. This work studies the inference of successful and unsuccessful intentions to speak from accelerometer data. This is chosen because it is privacy-preserving and feasible for in-the-wild settings since it can be placed in a smart badge. Data from a real-life social networking event is used to train a machine-learning model that aims to infer intentions to speak. A subset of unsuccessful intention-to-speak cases in the data is annotated. The model is trained on the successful intentions to speak and evaluated on both the successful and unsuccessful cases. In conclusion, there is useful information in accelerometer data, but not enough to reliably capture intentions to speak. For example, posture shifts are correlated with intentions to speak, but people also often shift posture without having an intention to speak, or have an intention to speak without shifting their posture. More modalities are likely needed to reliably infer intentions to speak.

In emergency situations, the high-speed movement of an ambulance through the city streets can be hindered by vehicular traffic. This work presents a method for detecting emergency vehicle sirens in real time. To obtain the audio fingerprint of a Hi-Lo siren, DSP and signal symbolization techniques were applied, which were contrasted against an audio classifier based on a deep neural network, using the same 280 audios of ambient sounds and 52 Hi-Lo siren audios dataset. In both methods, some classification accuracy metrics were evaluated based on its confusion matrix, resulting in the DSP algorithm having a slightly lower accuracy than the DNN model, however, it offers a self-explanatory, adjustable, portable, high performance and lower energy and consumption that makes it a more viable lower cost ADAS implementation to identify Hi-Lo sirens in real time., Comment: in Spanish language

Patents provide a rich source of information about design innovations. Patent mining techniques employ various technologies, such as text mining, machine learning, natural language processing, and ontology-building techniques. An automated graph data modelling method is proposed for extracting functional representations for building a semantic database of patents of mechanical designs. The method has several benefits: The schema-free characteristic of the proposed graph modelling enables the ontology it is based on to evolve and generalise to upper ontologies across technology domains and to specify lower ontologies to more specific domains. Graph modelling benefits from enhanced performance of deep queries across many levels of relationships and interactions and provides efficient storage. Graph modelling also enables visualisation libraries to use the graph data structure immediately, avoiding the need for graph extraction programs from relational databases. Patent/Design comparisons are computed by search queries using counting of overlaps of different levels and weights. This work has produced the PatMine SolidWorks Add-in \c{opyright}, which compares annotated CAD designs with patents and highlights overlapping design concepts. The patent annotation extracts its functional analysis, representing its structure as geometric feature interactions. Additional features such as full-text search and semantic search of the PatMine patents database are available, and graph analytic methods and machine learning algorithms are enabled and can be implemented as plug-ins in future work. Keywords: Patent Mining; Semantic Analysis; Functional Analysis Diagrams; Graph Data Modelling; Visualisation; Similarity Scoring; Big Data Analytics; Machine Learning; Artificial Intelligence; Natural Language Processing, Comment: 20 pages, 8 figures, to be submitted later for peer review

Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images. The inability of CNNs to generalize across magnification scales can result in sub-optimal performance on external datasets. This study aims to evaluate the robustness of various deep learning architectures in the analysis of breast cancer histopathological images with varying magnification scales at training and testing stages. Here we explore and compare the performance of multiple deep learning architectures, including CNN-based ResNet and MobileNet, self-attention-based Vision Transformers and Swin Transformers, and token-mixing models, such as FNet, ConvMixer, MLP-Mixer, and WaveMix. The experiments are conducted using the BreakHis dataset, which contains breast cancer histopathological images at varying magnification levels. We show that performance of WaveMix is invariant to the magnification of training and testing data and can provide stable and good classification accuracy. These evaluations are critical in identifying deep learning architectures that can robustly handle changes in magnification scale, ensuring that scale changes across anatomical structures do not disturb the inference results., Comment: 6 pages, 3 figures

Stress has a great effect on people's lives that can not be understated. While it can be good, since it helps humans to adapt to new and different situations, it can also be harmful when not dealt with properly, leading to chronic stress. The objective of this paper is developing a stress monitoring solution, that can be used in real life, while being able to tackle this challenge in a positive way. The SMILE data set was provided to team Anxolotl, and all it was needed was to develop a robust model. We developed a supervised learning model for classification in Python, presenting the final result of 64.1% in accuracy and a f1-score of 54.96%. The resulting solution stood the robustness test, presenting low variation between runs, which was a major point for it's possible integration in the Anxolotl app in the future., Comment: 7 pages, 3 figures, 2 tables IEEE 44th International Engineering in Medicine and Biology Conference

Clinical Cohort Studies (CCS), such as randomized clinical trials, are a great source of documented clinical research. Ideally, a clinical expert inspects these articles for exploratory analysis ranging from drug discovery for evaluating the efficacy of existing drugs in tackling emerging diseases to the first test of newly developed drugs. However, more than 100 articles are published daily on a single prevalent disease like COVID-19 in PubMed. As a result, it can take days for a physician to find articles and extract relevant information. Can we develop a system to sift through the long list of these articles faster and document the crucial takeaways from each of these articles? In this work, we propose CCS Explorer, an end-to-end system for relevance prediction of sentences, extractive summarization, and patient, outcome, and intervention entity detection from CCS. CCS Explorer is packaged in a web-based graphical user interface where the user can provide any disease name. CCS Explorer then extracts and aggregates all relevant information from articles on PubMed based on the results of an automatically generated query produced on the back-end. For each task, CCS Explorer fine-tunes pre-trained language representation models based on transformers with additional layers. The models are evaluated using two publicly available datasets. CCS Explorer obtains a recall of 80.2%, AUC-ROC of 0.843, and an accuracy of 88.3% on sentence relevance prediction using BioBERT and achieves an average Micro F1-Score of 77.8% on Patient, Intervention, Outcome detection (PIO) using PubMedBERT. Thus, CCS Explorer can reliably extract relevant information to summarize articles, saving time by $\sim \text{660}\times$., Comment: Accepted at IEEE BigData 2022

We present a geometric version of Quickest Change Detection (QCD) and Quickest Hub Discovery (QHD) tests in correlation structures that allows us to include and combine new information with distance metrics. The topic falls within the scope of sequential, nonparametric, high-dimensional QCD and QHD, from which state-of-the-art settings developed global and local summary statistics from asymptotic Random Matrix Theory (RMT) to detect changes in random matrix law. These settings work only for uncorrelated pre-change variables. With our geometric version of the tests via clustering, we can test the hypothesis that we can improve state-of-the-art settings for QHD, by combining QCD and QHD simultaneously, as well as including information about pre-change time-evolution in correlations. We can work with correlated pre-change variables and test if the time-evolution of correlation improves performance. We prove test consistency and design test hypothesis based on clustering performance. We apply this solution to financial time series correlations. Future developments on this topic are highly relevant in finance for Risk Management, Portfolio Management, and Market Shocks Forecasting which can save billions of dollars for the global economy. We introduce the Diversification Measure Distribution (DMD) for modeling the time-evolution of correlations as a function of individual variables which consists of a Dirichlet-Multinomial distribution from a distance matrix of rolling correlations with a threshold. Finally, we are able to verify all these hypotheses.

Hyperbox-based machine learning algorithms are an important and popular branch of machine learning in the construction of classifiers using fuzzy sets and logic theory and neural network architectures. This type of learning is characterised by many strong points of modern predictors such as a high scalability, explainability, online adaptation, effective learning from a small amount of data, native ability to deal with missing data and accommodating new classes. Nevertheless, there is no comprehensive existing package for hyperbox-based machine learning which can serve as a benchmark for research and allow non-expert users to apply these algorithms easily. hyperbox-brain is an open-source Python library implementing the leading hyperbox-based machine learning algorithms. This library exposes a unified API which closely follows and is compatible with the renowned scikit-learn and numpy toolboxes. The library may be installed from Python Package Index (PyPI) and the conda package manager and is distributed under the GPL-3 license. The source code, documentation, detailed tutorials, and the full descriptions of the API are available at https://uts-caslab.github.io/hyperbox-brain., Comment: 11 pages

The advent of the internet, followed shortly by the social media made it ubiquitous in consuming and sharing information between anyone with access to it. The evolution in the consumption of media driven by this change, led to the emergence of images as means to express oneself, convey information and convince others efficiently. With computer vision algorithms progressing radically over the last decade, it is become easier and easier to study at scale the role of images in the flow of information online. While the research questions and overall pipelines differ radically, almost all start with a crucial first step - evaluation of global perceptual similarity between different images. That initial step is crucial for overall pipeline performance and processes most images. A number of algorithms are available and currently used to perform it, but so far no comprehensive review was available to guide the choice of researchers as to the choice of an algorithm best suited to their question, assumptions and computational resources. With this paper we aim to fill this gap, showing that classical computer vision methods are not necessarily the best approach, whereas a pair of relatively little used methods - Dhash perceptual hash and SimCLR v2 ResNets achieve excellent performance, scale well and are computationally efficient., Comment: 26 pages, 10 figures

Speech emotion recognition systems have high prediction latency because of the high computational requirements for deep learning models and low generalizability mainly because of the poor reliability of emotional measurements across multiple corpora. To solve these problems, we present a speech emotion recognition system based on a reductionist approach of decomposing and analyzing syllable-level features. Mel-spectrogram of an audio stream is decomposed into syllable-level components, which are then analyzed to extract statistical features. The proposed method uses formant attention, noise-gate filtering, and rolling normalization contexts to increase feature processing speed and tolerance to adversity. A set of syllable-level formant features is extracted and fed into a single hidden layer neural network that makes predictions for each syllable as opposed to the conventional approach of using a sophisticated deep learner to make sentence-wide predictions. The syllable level predictions help to achieve the real-time latency and lower the aggregated error in utterance level cross-corpus predictions. The experiments on IEMOCAP (IE), MSP-Improv (MI), and RAVDESS (RA) databases show that the method archives real-time latency while predicting with state-of-the-art cross-corpus unweighted accuracy of 47.6% for IE to MI and 56.2% for MI to IE., Comment: Significant revisions

The trade-off between throughput and image quality is an inherent challenge in microscopy. To improve throughput, compressive imaging under-samples image signals; the images are then computationally reconstructed by solving a regularized inverse problem. Compared to traditional regularizers, Deep Learning based methods have achieved greater success in compression and image quality. However, the information loss in the acquisition process sets the compression bounds. Further improvement in compression, without compromising the reconstruction quality is thus a challenge. In this work, we propose differentiable compressive fluorescence microscopy ($\partial \mu$) which includes a realistic generalizable forward model with learnable-physical parameters (e.g. illumination patterns), and a novel physics-inspired inverse model. The cascaded model is end-to-end differentiable and can learn optimal compressive sampling schemes through training data. With our model, we performed thousands of numerical experiments on various compressive microscope configurations. We show that learned sampling encodes important information about the specimens in the illumination field of the microscope allowing higher compression up to $\times 1024$. We further utilize our framework for Task Aware Compression. The experimental results show superior performance on the cell segmentation task.

Creativity in social robots requires further attention in the interdisciplinary field of Human-Robot Interaction (HRI). This paper investigates the hypothesised connection between the perceived creative agency and the animacy of social robots. The goal of this work is to assess the relevance of robot movements in the attribution of creativity to robots. The results of this work inform the design of future Human-Robot Creative Interactions (HRCI). The study uses a storytelling game based on visual imagery inspired by the game 'Story Cubes' to explore the perceived creative agency of social robots. This game is used to tell a classic story for children with an alternative ending. A 2x2 experiment was designed to compare two conditions: the robot telling the original version of the story and the robot plot-twisting the end of the story. A Robotis Mini humanoid robot was used for the experiment. As a novel contribution, we propose an adaptation of the Short Scale Creative Self scale (SSCS) to measure perceived creative agency in robots. We also use the Godspeed scale to explore different attributes of social robots in this setting. We did not obtain significant main effects of the robot movements or the story in the participants' scores. However, we identified significant main effects of the robot movements in features of animacy, likeability, and perceived safety. This initial work encourages further studies experimenting with different robot embodiment and movements to evaluate the perceived creative agency in robots and inform the design of future robots that participate in creative interactions., Comment: This paper is under review for the Frontiers in Robotics and AI journal since April 2021

This paper deals with the highly challenging problem of reconstructing the shape of a refracting object from a single image of its resulting caustic. Due to the ubiquity of transparent refracting objects in everyday life, reconstruction of their shape entails a multitude of practical applications. The recent Shape from Caustics (SfC) method casts the problem as the inverse of a light propagation simulation for synthesis of the caustic image, that can be solved by a differentiable renderer. However, the inherent complexity of light transport through refracting surfaces currently limits the practicability with respect to reconstruction speed and robustness. To address these issues, we introduce Neural-Shape from Caustics (N-SfC), a learning-based extension that incorporates two components into the reconstruction pipeline: a denoising module, which alleviates the computational cost of the light transport simulation, and an optimization process based on learned gradient descent, which enables better convergence using fewer iterations. Extensive experiments demonstrate the effectiveness of our neural extensions in the scenario of quality control in 3D glass printing, where we significantly outperform the current state-of-the-art in terms of computational speed and final surface error., Comment: Project Page: https://graphics.tu-bs.de/publications/kassubeck2021n-sfc

Counting objects is a fundamental but challenging problem. In this paper, we propose diffusion-based, geometry-free, and learning-free methodologies to count the number of objects in images. The main idea is to represent each object by a unique index value regardless of its intensity or size, and to simply count the number of index values. First, we place different vectors, refer to as seed vectors, uniformly throughout the mask image. The mask image has boundary information of the objects to be counted. Secondly, the seeds are diffused using an edge-weighted harmonic variational optimization model within each object. We propose an efficient algorithm based on an operator splitting approach and alternating direction minimization method, and theoretical analysis of this algorithm is given. An optimal solution of the model is obtained when the distributed seeds are completely diffused such that there is a unique intensity within each object, which we refer to as an index. For computational efficiency, we stop the diffusion process before a full convergence, and propose to cluster these diffused index values. We refer to this approach as Counting Objects by Diffused Index (CODI). We explore scalar and multi-dimensional seed vectors. For Scalar seeds, we use Gaussian fitting in histogram to count, while for vector seeds, we exploit a high-dimensional clustering method for the final step of counting via clustering. The proposed method is flexible even if the boundary of the object is not clear nor fully enclosed. We present counting results in various applications such as biological cells, agriculture, concert crowd, and transportation. Some comparisons with existing methods are presented.

Graph Representation Learning (GRL) methods opened new avenues for addressing complex, real-world problems represented by graphs. However, many graphs used in these applications comprise millions of nodes and billions of edges and are beyond the capabilities of current methods and software implementations. We present GRAPE, a software resource for graph processing and embedding that can scale with big graphs by using specialized and smart data structures, algorithms, and a fast parallel implementation of random walk-based methods. Compared with state-of-the-art software resources, GRAPE shows an improvement of orders of magnitude in empirical space and time complexity, as well as a competitive edge and node label prediction performance. GRAPE comprises about 1.7 million well-documented lines of Python and Rust code and provides 69 node embedding methods, 25 inference models, a collection of efficient graph processing utilities and over 80,000 graphs from the literature and other sources. Standardized interfaces allow seamless integration of third-party libraries, while ready-to-use and modular pipelines permit an easy-to-use evaluation of GRL methods, therefore also positioning GRAPE as a software resource to perform a fair comparison between methods and libraries for graph processing and embedding.

We present a Spiking Neural Network (SNN) based Sparse Distributed Memory (SDM) implemented on the Nengo framework. We have based our work on previous work by Furber et al, 2004, implementing SDM using N-of-M codes. As an integral part of the SDM design, we have implemented Correlation Matrix Memory (CMM) using SNN on Nengo. Our SNN implementation uses Leaky Integrate and Fire (LIF) spiking neuron models on Nengo. Our objective is to understand how well SNN-based SDMs perform in comparison to conventional SDMs. Towards this, we have simulated both conventional and SNN-based SDM and CMM on Nengo. We observe that SNN-based models perform similarly as the conventional ones. In order to evaluate the performance of different SNNs, we repeated the experiment using Adaptive-LIF, Spiking Rectified Linear Unit, and Izhikevich models and obtained similar results. We conclude that it is indeed feasible to develop some types of associative memories using spiking neurons whose memory capacity and other features are similar to the performance without SNNs. Finally we have implemented an application where MNIST images, encoded with N-of-M codes, are associated with their labels and stored in the SNN-based SDM., Comment: 8 pages, 11 figures, accepted as poster in Bernstein Conference 2021

Geometric Semantic Genetic Programming (GSGP) is a state-of-the-art machine learning method based on evolutionary computation. GSGP performs search operations directly at the level of program semantics, which can be done more efficiently then operating at the syntax level like most GP systems. Efficient implementations of GSGP in C++ exploit this fact, but not to its full potential. This paper presents GSGP-CUDA, the first CUDA implementation of GSGP and the most efficient, which exploits the intrinsic parallelism of GSGP using GPUs. Results show speedups greater than 1,000X relative to the state-of-the-art sequential implementation., Comment: 14 pages, 3 figures

We present PSEUDo, an adaptive feature learning technique for exploring visual patterns in multi-track sequential data. Our approach is designed with the primary focus to overcome the uneconomic retraining requirements and inflexible representation learning in current deep learning-based systems. Multi-track time series data are generated on an unprecedented scale due to increased sensors and data storage. These datasets hold valuable patterns, like in neuromarketing, where researchers try to link patterns in multivariate sequential data from physiological sensors to the purchase behavior of products and services. But a lack of ground truth and high variance make automatic pattern detection unreliable. Our advancements are based on a novel query-aware locality-sensitive hashing technique to create a feature-based representation of multivariate time series windows. Most importantly, our algorithm features sub-linear training and inference time. We can even accomplish both the modeling and comparison of 10,000 different 64-track time series, each with 100 time steps (a typical EEG dataset) under 0.8 seconds. This performance gain allows for a rapid relevance feedback-driven adaption of the underlying pattern similarity model and enables the user to modify the speed-vs-accuracy trade-off gradually. We demonstrate superiority of PSEUDo in terms of efficiency, accuracy, and steerability through a quantitative performance comparison and a qualitative visual quality comparison to the state-of-the-art algorithms in the field. Moreover, we showcase the usability of PSEUDo through a case study demonstrating our visual pattern retrieval concepts in a large meteorological dataset. We find that our adaptive models can accurately capture the user's notion of similarity and allow for an understandable exploratory visual pattern retrieval in large multivariate time series datasets., Comment: 11 pages including 2 pages for references, 10 figures including 1 teaser figure, sumbitted to IEEE VIS 2021, gitlab repository https://git.science.uu.nl/vig/sublinear-algorithms-for-va/locality-sensitive-hashing-visual-analytics

Machine learning (ML) research has yielded powerful tools for training accurate prediction models despite complex multivariate associations (e.g. interactions and heterogeneity). In fields such as medicine, improved interpretability of ML modeling is required for knowledge discovery, accountability, and fairness. Rule-based ML approaches such as Learning Classifier Systems (LCSs) strike a balance between predictive performance and interpretability in complex, noisy domains. This work introduces the LCS Discovery and Visualization Environment (LCS-DIVE), an automated LCS model interpretation pipeline for complex biomedical classification. LCS-DIVE conducts modeling using a new scikit-learn implementation of ExSTraCS, an LCS designed to overcome noise and scalability in biomedical data mining yielding human readable IF:THEN rules as well as feature-tracking scores for each training sample. LCS-DIVE leverages feature-tracking scores and/or rules to automatically guide characterization of (1) feature importance (2) underlying additive, epistatic, and/or heterogeneous patterns of association, and (3) model-driven heterogeneous instance subgroups via clustering, visualization generation, and cluster interrogation. LCS-DIVE was evaluated over a diverse set of simulated genetic and benchmark datasets encoding a variety of complex multivariate associations, demonstrating its ability to differentiate between them and then applied to characterize associations within a real-world study of pancreatic cancer., Comment: 21 pages, 11 figures, submitted for review on 4/26/21

Central to the application of many multi-view geometry algorithms is the extraction of matching points between multiple viewpoints, enabling classical tasks such as camera pose estimation and 3D reconstruction. Many approaches that characterize these points have been proposed based on hand-tuned appearance models or data-driven learning methods. We propose Soft Expectation and Deep Maximization (SEDM), an iterative unsupervised learning process that directly optimizes the repeatability of the features by posing the problem in a similar way to expectation maximization (EM). We found convergence to be reliable and the new model to be more lighting invariant and better at localize the underlying 3D points in a scene, improving SfM quality when compared to other state of the art deep learning detectors., Comment: 9 pages, 3 figures, 2 tables

This paper presents a systematic review of Python packages with a focus on time series analysis. The objective is to provide (1) an overview of the different time series analysis tasks and preprocessing methods implemented, and (2) an overview of the development characteristics of the packages (e.g., documentation, dependencies, and community size). This review is based on a search of literature databases as well as GitHub repositories. Following the filtering process, 40 packages were analyzed. We classified the packages according to the analysis tasks implemented, the methods related to data preparation, and the means for evaluating the results produced (methods and access to evaluation data). We also reviewed documentation aspects, the licenses, the size of the packages' community, and the dependencies used. Among other things, our results show that forecasting is by far the most frequently implemented task, that half of the packages provide access to real datasets or allow generating synthetic data, and that many packages depend on a few libraries (the most used ones being numpy, scipy and pandas). We hope that this review can help practitioners and researchers navigate the space of Python packages dedicated to time series analysis. We will provide an updated list of the reviewed packages online at https://siebert-julien.github.io/time-series-analysis-python/., Comment: 12 pages, 3 figures, 4 tables, accepted to ITISE2021

The number of published PDF documents has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature. We demonstrate how a sequence of PDF printing commands can be used as input into a neural network and how the network can learn to classify each printing command according to its structural function in the page. This approach has three advantages: First, it can distinguish among more fine-grained labels (typically 10-20 labels as opposed to 1-5 with visual methods), which results in a more accurate and detailed document structure resolution. Second, it can take into account the text flow across pages more naturally compared to visual methods because it can concatenate the printing commands of sequential pages. Last, our proposed method needs less memory and it is computationally less expensive than visual methods. This allows us to deploy such models in production environments at a much lower cost. Through extensive architectural search in combination with advanced feature engineering, we were able to implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels. The best model we achieved is currently served in production environments on our Corpus Conversion Service (CCS), which was presented at KDD18 (arXiv:1806.02284). This model enhances the capabilities of CCS significantly, as it eliminates the need for human annotated label ground-truth for every unseen document layout. This proved particularly useful when applied to a huge corpus of PDF articles related to COVID-19., Comment: 9 pages, 2 tables, 4 figures, uses aaai21.sty. Accepted at the "Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21)". Received the "IAAI-21 Innovative Application Award"

Dynamic Time Warping (DTW) is a popular similarity measure for aligning and comparing time series. Due to DTW's high computation time, lower bounds are often employed to screen poor matches. Many alternative lower bounds have been proposed, providing a range of different trade-offs between tightness and computational efficiency. LB Keogh provides a useful trade-off in many applications. Two recent lower bounds, LB Improved and LB Enhanced, are substantially tighter than LB Keogh. All three have the same worst case computational complexity - linear with respect to series length and constant with respect to window size. We present four new DTW lower bounds in the same complexity class. LB Petitjean is substantially tighter than LB Improved, with only modest additional computational overhead. LB Webb is more efficient than LB Improved, while often providing a tighter bound. LB Webb is always tighter than LB Keogh. The parameter free LB Webb is usually tighter than LB Enhanced. A parameterized variant, LB Webb Enhanced, is always tighter than LB Enhanced. A further variant, LB Webb*, is useful for some constrained distance functions. In extensive experiments, LB Webb proves to be very effective for nearest neighbor search., Comment: 26 pages, 23 figures, expanded version of a paper accepted for publication in Pattern Recognition. This revision fixed minor typos in the two algorithms

Is multiplication really necessary for deep neural networks? Here we propose just adding two IEEE754 floating-point numbers with an integer-add instruction in place of a floating-point multiplication instruction. We show that ResNet can be trained using this operation with competitive classification accuracy. Our proposal did not require any methods to solve instability and decrease in accuracy, which is common in low-precision training. In some settings, we may obtain equal accuracy to the baseline FP32 result. This method will enable eliminating the multiplications in deep neural-network training and inference., Comment: 6 pages, 1 figure, accepted as a workshop paper at NeurIPS2020

The world is going through one of the most dangerous pandemics of all time with the rapid spread of the novel coronavirus (COVID-19). According to the World Health Organisation, the most effective way to thwart the transmission of coronavirus is to wear medical face masks. Monitoring the use of face masks in public places has been a challenge because manual monitoring could be unsafe. This paper proposes an architecture for detecting medical face masks for deployment on resource-constrained endpoints having extremely low memory footprints. A small development board with an ARM Cortex-M7 microcontroller clocked at 480 Mhz and having just 496 KB of framebuffer RAM, has been used for the deployment of the model. Using the TensorFlow Lite framework, the model is quantized to further reduce its size. The proposed model is 138 KB post quantization and runs at the inference speed of 30 FPS., Comment: 11 pages, Published in Springer LNEE at http://link.springer.com/chapter/10.1007%2F978-981-16-0749-3_52

This paper presents the 'hyper-sinh', a variation of the m-arcsinh activation function suitable for Deep Learning (DL)-based algorithms for supervised learning, such as Convolutional Neural Networks (CNN). hyper-sinh, developed in the open source Python libraries TensorFlow and Keras, is thus described and validated as an accurate and reliable activation function for both shallow and deep neural networks. Improvements in accuracy and reliability in image and text classification tasks on five (N = 5) benchmark data sets available from Keras are discussed. Experimental results demonstrate the overall competitive classification performance of both shallow and deep neural networks, obtained via this novel function. This function is evaluated with respect to gold standard activation functions, demonstrating its overall competitive accuracy and reliability for both image and text classification., Comment: 19 pages, 6 listings/Python code snippets, 4 figures, 5 tables

Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of CNN models. These applications use third-party solutions for inference, making them less user-friendly and unsuitable for high-performance image analysis. To make deployment of CNNs user-friendly and feasible on low-end machines, we have developed a new platform, FastPathology, using the FAST framework and C++. It minimizes memory usage for reading and processing WSIs, deployment of CNN models, and real-time interactive visualization of results. Runtime experiments were conducted on four different use cases, using different architectures, inference engines, hardware configurations and operating systems. Memory usage for reading, visualizing, zooming and panning a WSI were measured, using FastPathology and three existing platforms. FastPathology performed similarly in terms of memory to the other C++ based application, while using considerably less than the two Java-based platforms. The choice of neural network model, inference engine, hardware and processors influenced runtime considerably. Thus, FastPathology includes all steps needed for efficient visualization and processing of WSIs in a single application, including inference of CNNs with real-time display of the results. Source code, binary releases and test data can be found online on GitHub at https://github.com/SINTEFMedtek/FAST-Pathology/., Comment: 12 pages, 4 figures, submitted to IEEE Access

We present methods to serialize and deserialize tree ensembles that optimize inference latency when models are not already loaded into memory. This arises whenever models are larger than memory, but also systematically when models are deployed on low-resource devices, such as in the Internet of Things, or run as Web micro-services where resources are allocated on demand. Our packed serialized trees (PACSET) encode reference locality in the layout of a tree ensemble using principles from external memory algorithms. The layout interleaves correlated nodes across multiple trees, uses leaf cardinality to collocate the nodes on the most popular paths and is optimized for the I/O blocksize. The result is that each I/O yields a higher fraction of useful data, leading to a 2-6 times reduction in classification latency for interactive workloads.

The Fast Tracker (FTK) is an ATLAS trigger upgrade built for full event, low-latency, high-rate tracking. The FTK core, made of 9U VME boards, performs the most demanding computational task. The Associative Memory Board Serial Link Processor (AMB) and the Auxiliary card (AUX), plugged on the front and back sides of the same VME slot, constitute the Processing Unit (PU), which finds tracks using hits from 8 layers of the inner detector. The PU works in pipeline with the Second Stage Board (SSB), which finds 12-layer tracks by adding extra hits to the identified tracks. In the designed configuration, 16 PUs and 4 SSBs are installed in a VME crate. The high power-consumption of the AMB, AUX and SSB (respectively of about 250 W, 70 W and 160 W per board) required the development of a custom cooling system. Even though the expected power consumption for each VME crate of the FTK system is high compared to a common VME setup, the 8 FTK core crates will use $\approx$ 60 kW, which is just a fraction of the power and the space needed for a CPU farm performing the same task. We report on the integration of 32 PUs and 8 SSBs inside the FTK system, on the infrastructures needed to run and cool them, and on the tests performed to verify the system processing rate and the temperature stability at a safe value., Comment: Real Time 2020 conference, 8 pages

The ReLU activation function (AF) has been extensively applied in deep neural networks, in particular Convolutional Neural Networks (CNN), for image classification despite its unresolved dying ReLU problem, which poses challenges to reliable applications. This issue has obvious important implications for critical applications, such as those in healthcare. Recent approaches are just proposing variations of the activation function within the same unresolved dying ReLU challenge. This contribution reports a different research direction by investigating the development of an innovative quantum approach to the ReLU AF that avoids the dying ReLU problem by disruptive design. The Leaky ReLU was leveraged as a baseline on which the two quantum principles of entanglement and superposition were applied to derive the proposed Quantum ReLU (QReLU) and the modified-QReLU (m-QReLU) activation functions. Both QReLU and m-QReLU are implemented and made freely available in TensorFlow and Keras. This original approach is effective and validated extensively in case studies that facilitate the detection of COVID-19 and Parkinson Disease (PD) from medical images. The two novel AFs were evaluated in a two-layered CNN against nine ReLU-based AFs on seven benchmark datasets, including images of spiral drawings taken via graphic tablets from patients with Parkinson Disease and healthy subjects, and point-of-care ultrasound images on the lungs of patients with COVID-19, those with pneumonia and healthy controls. Despite a higher computational cost, results indicated an overall higher classification accuracy, precision, recall and F1-score brought about by either quantum AFs on five of the seven bench-mark datasets, thus demonstrating its potential to be the new benchmark or gold standard AF in CNNs and aid image classification tasks involved in critical applications, such as medical diagnoses of COVID-19 and PD., Comment: 30 pages, 4 listings/Python code snippets, 2 figures, 8 tables

The purpose of this work is to highlight the content of the Microsoft Recommenders repository and show how it can be used to reduce the time involved in developing recommender systems. The open source repository provides python utilities to simplify common recommender-related data science work as well as example Jupyter notebooks that demonstrate use of the algorithms and tools under various environments., Comment: pages: 2; submitted to: RecSys '19

While the number of children with diagnosed autism spectrum disorder (ASD) continues to rise from year to year, there is still no universal approach to autism diagnosis and treatment. A great variety of different tools and approaches for the on-site diagnostic are available right now, however, a big percent of parents have no access to them and they tend to search for the available tools and correction programs on the Internet. Lack of money, absence of qualified specialists, and low level of trust to the correction methods are the main issues that affect the in-time diagnoses of ASD and which need to be solved to get the early treatment for the little patients. Understanding the importance of this issue our team decided to investigate new methods of the online autism diagnoses and develop the algorithm that will be able to predict the chances of ASD according to the information from the gaze activity of the child. The results that we got during the experiments show supported our idea that eye-tracking technology is one of the most promising tools for the early detection of the eye-movement features that can be markers of the ASD. Moreover, we have conducted a series of experiments to ensure that our approach has a reliable result on the cheap webcam systems. Thus, this approach can be used as an additional first screening tool for the home monitoring of the early child development and ASD connected disorders monitoring. The further development of eye-tracking based autism diagnosis has a big potential of usage and can be further implemented in the daily practice for practical specialists and parents., Comment: 11 pages, 7 Figures

To cope with the rapid growth in available data, the efficiency of data analysis and machine learning libraries has recently received increased attention. Although great advancements have been made in traditional array-based computations, most are limited by the resources available on a single computation node. Consequently, novel approaches must be made to exploit distributed resources, e.g. distributed memory architectures. To this end, we introduce HeAT, an array-based numerical programming framework for large-scale parallel processing with an easy-to-use NumPy-like API. HeAT utilizes PyTorch as a node-local eager execution engine and distributes the workload on arbitrarily large high-performance computing systems via MPI. It provides both low-level array computations, as well as assorted higher-level algorithms. With HeAT, it is possible for a NumPy user to take full advantage of their available resources, significantly lowering the barrier to distributed data analysis. When compared to similar frameworks, HeAT achieves speedups of up to two orders of magnitude., Comment: 10 pages, 8 figures, 5 listings, 1 table

The paper describes how to detect malicious executable files based on static analysis of their binary content. The stages of pre-processing and cleaning data extracted from different areas of executable files are analyzed. Methods of encoding categorical attributes of executable files are considered, as are ways to reduce the feature field dimension and select characteristic features in order to effectively represent samples of binary executable files for further training classifiers. An ensemble training approach was applied in order to aggregate forecasts from each classifier, and an ensemble of classifiers of various feature groups of executable file attributes was created in order to subsequently develop a system for detecting malicious files in an uninsulated environment., Comment: 36 pages, 13 figures, 6 tables

The number of groups ($g$) in group convolution (GConv) is selected to boost the predictive performance of deep neural networks (DNNs) in a compute and parameter efficient manner. However, we show that naive selection of $g$ in GConv creates an imbalance between the computational complexity and degree of data reuse, which leads to suboptimal energy efficiency in DNNs. We devise an optimum group size model, which enables a balance between computational cost and data movement cost, thus, optimize the energy-efficiency of DNNs. Based on the insights from this model, we propose an "energy-efficient group convolution" (E2GC) module where, unlike the previous implementations of GConv, the group size ($G$) remains constant. Further, to demonstrate the efficacy of the E2GC module, we incorporate this module in the design of MobileNet-V1 and ResNeXt-50 and perform experiments on two GPUs, P100 and P4000. We show that, at comparable computational complexity, DNNs with constant group size (E2GC) are more energy-efficient than DNNs with a fixed number of groups (F$g$GC). For example, on P100 GPU, the energy-efficiency of MobileNet-V1 and ResNeXt-50 is increased by 10.8% and 4.73% (respectively) when E2GC modules substitute the F$g$GC modules in both the DNNs. Furthermore, through our extensive experimentation with ImageNet-1K and Food-101 image classification datasets, we show that the E2GC module enables a trade-off between generalization ability and representational power of DNN. Thus, the predictive performance of DNNs can be optimized by selecting an appropriate $G$. The code and trained models are available at https://github.com/iithcandle/E2GC-release., Comment: Accepted as a conference paper in 2020 33rd International Conference on VLSI Design and 2020 19th International Conference on Embedded Systems (VLSID)

Machine learning is becoming increasingly important to control the behavior of safety and financially critical components in sophisticated environments, where the inability to understand learned components in general, and neural nets in particular, poses serious obstacles to their adoption. Explainability and interpretability methods for learned systems have gained considerable academic attention, but the focus of current approaches on only one aspect of explanation, at a fixed level of abstraction, and limited if any formal guarantees, prevents those explanations from being digestible by the relevant stakeholders (e.g., end users, certification authorities, engineers) with their diverse backgrounds and situation-specific needs. We introduce Fanoos, a framework for combining formal verification techniques, heuristic search, and user interaction to explore explanations at the desired level of granularity and fidelity. We demonstrate the ability of Fanoos to produce and adjust the abstractness of explanations in response to user requests on a learned controller for an inverted double pendulum and on a learned CPU usage model., Comment: 60 pages, 20 pages main body, 128 references, 3 figures, 5 tables, 12 pseudocode blocks Update 24 Sep. 2020 : Added a pointer to further, external content: Append Section E. Update 20 Mar. 2021: Substantial additions. Further explanations of process, with far more pseudocode. Some corrections to a previous description; see errata section. Also briefly describe a few implemented extensions

After being collected for patient care, Observational Health Data (OHD) can further benefit patient well-being by sustaining the development of health informatics and medical research. Vast potential is unexploited because of the fiercely private nature of patient-related data and regulations to protect it. Generative Adversarial Networks (GANs) have recently emerged as a groundbreaking way to learn generative models that produce realistic synthetic data. They have revolutionized practices in multiple domains such as self-driving cars, fraud detection, digital twin simulations in industrial sectors, and medical imaging. The digital twin concept could readily apply to modelling and quantifying disease progression. In addition, GANs posses many capabilities relevant to common problems in healthcare: lack of data, class imbalance, rare diseases, and preserving privacy. Unlocking open access to privacy-preserving OHD could be transformative for scientific research. In the midst of COVID-19, the healthcare system is facing unprecedented challenges, many of which of are data related for the reasons stated above. Considering these facts, publications concerning GAN applied to OHD seemed to be severely lacking. To uncover the reasons for this slow adoption, we broadly reviewed the published literature on the subject. Our findings show that the properties of OHD were initially challenging for the existing GAN algorithms (unlike medical imaging, for which state-of-the-art model were directly transferable) and the evaluation synthetic data lacked clear metrics. We find more publications on the subject than expected, starting slowly in 2017, and since then at an increasing rate. The difficulties of OHD remain, and we discuss issues relating to evaluation, consistency, benchmarking, data modelling, and reproducibility., Comment: 31 pages (10 in previous version), not including references and glossary, 51 in total. Inclusion of a large number of recent publications and expansion of the discussion accordingly

This thesis surveys the research in patch-based synthesis and algorithms for finding correspondences between small local regions of images. We additionally explore a large kind of applications of this new fast randomized matching technique. One of the algorithms we have studied in particular is PatchMatch, can find similar regions or "patches" of an image one to two orders of magnitude faster than previous techniques. The algorithmic program is driven by applying mathematical properties of nearest neighbors in natural images. It is observed that neighboring correspondences tend to be similar or "coherent" and use this observation in algorithm in order to quickly converge to an approximate solution. The algorithm is the most general form can find k-nearest neighbor matching, using patches that translate, rotate, or scale, using arbitrary descriptors, and between two or more images. Speed-ups are obtained over various techniques in an exceeding range of those areas. We have explored many applications of PatchMatch matching algorithm. In computer graphics, we have explored removing unwanted objects from images, seamlessly moving objects in images, changing image aspect ratios, and video summarization. In computer vision we have explored denoising images, object detection, detecting image forgeries, and detecting symmetries. We conclude by discussing the restrictions of our algorithmic program, GPU implementation and areas for future analysis., Comment: 117 pages, 38 figures, in Persian

Drone susceptibility to jamming or spoofing attacks of GPS, RF, Wi-Fi, and operator signals presents a danger to future medical delivery systems. A detection framework capable of sensing attacks on drones could provide the capability for active responses. The identification of interference attacks has applicability in medical delivery, disaster zone relief, and FAA enforcement against illegal jamming activities. A gap exists in the literature for solo or swarm-based drones to identify radio frequency spectrum attacks. Any non-delivery specific function, such as attack sensing, added to a drone involves a weight increase and additional complexity; therefore, the value must exceed the disadvantages. Medical delivery, high-value cargo, and disaster zone applications could present a value proposition which overcomes the additional costs. The paper examines types of attacks against drones and describes a framework for designing an attack detection system with active response capabilities for improving the reliability of delivery and other medical applications., Comment: 7 pages, 1 figures, 5 tables

The energy consumed by running large deep neural networks (DNNs) on hardware accelerators is dominated by the need for lots of fast memory to store both states and weights. This large required memory is currently only economically viable through DRAM. Although DRAM is high-throughput and low-cost memory (costing 20X less than SRAM), its long random access latency is bad for the unpredictable access patterns in spiking neural networks (SNNs). In addition, accessing data from DRAM costs orders of magnitude more energy than doing arithmetic with that data. SNNs are energy-efficient if local memory is available and few spikes are generated. This paper reports on our developments over the last 5 years of convolutional and recurrent deep neural network hardware accelerators that exploit either spatial or temporal sparsity similar to SNNs but achieve SOA throughput, power efficiency and latency even with the use of DRAM for the required storage of the weights and states of large DNNs., Comment: To appear in 2019 IEEE Sig. Proc. Soc. Asilomar Conference on Signals, Systems, and Computers Session MP6b: Neuromorphic Computing (Invited)

The most widely used internal measure for clustering evaluation is the silhouette coefficient, whose naive computation requires a quadratic number of distance calculations, which is clearly unfeasible for massive datasets. Surprisingly, there are no known general methods to efficiently approximate the silhouette coefficient of a clustering with rigorously provable high accuracy. In this paper, we present the first scalable algorithm to compute such a rigorous approximation for the evaluation of clusterings based on any metric distances. Our algorithm hinges on a Probability Proportional to Size (PPS) sampling scheme, and, for any fixed $\varepsilon, \delta \in (0,1)$, it approximates the silhouette coefficient within a mere additive error $O(\varepsilon)$ with probability $1-\delta$, using a very small number of distance calculations. We also prove that the algorithm can be adapted to obtain rigorous approximations of other internal measures of clustering quality, such as cohesion and separation. Importantly, we provide a distributed implementation of the algorithm using the MapReduce model, which runs in constant rounds and requires only sublinear local space at each worker, which makes our estimation approach applicable to big data scenarios. We perform an extensive experimental evaluation of our silhouette approximation algorithm, comparing its performance to a number of baseline heuristics on real and synthetic datasets. The experiments provide evidence that, unlike other heuristics, our estimation strategy not only provides tight theoretical guarantees but is also able to return highly accurate estimations while running in a fraction of the time required by the exact computation, and that its distributed implementation is highly scalable, thus enabling the computation of internal measures for very large datasets for which the exact computation is prohibitive., Comment: 16 pages, 4 tables, 1 figure

Human affect recognition is an essential part of natural human-computer interaction. However, current methods are still in their infancy, especially for in-the-wild data. In this work, we introduce our submission to the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition. We propose a two-stream aural-visual analysis model to recognize affective behavior from videos. Audio and image streams are first processed separately and fed into a convolutional neural network. Instead of applying recurrent architectures for temporal analysis we only use temporal convolutions. Furthermore, the model is given access to additional features extracted during face-alignment. At training time, we exploit correlations between different emotion representations to improve performance. Our model achieves promising results on the challenging Aff-Wild2 database., Comment: 6 pages, 2 figures, Face and Gesture 2020 Workshop Paper (ABAW2020 competition)

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample. Adversarial attacks that render DNNs vulnerable in real life represent a serious threat in autonomous vehicles, malware filters, or biometric authentication systems. In this paper, we apply Fast Gradient Sign Method to introduce perturbations to a facial image dataset and then test the output on a different classifier that we trained ourselves, to analyze transferability of this method. Next, we craft a variety of different black-box attack algorithms on a facial image dataset assuming minimal adversarial knowledge, to further assess the robustness of DNNs in facial recognition. While experimenting with different image distortion techniques, we focus on modifying single optimal pixels by a large amount, or modifying all pixels by a smaller amount, or combining these two attack approaches. While our single-pixel attacks achieved about a 15% average decrease in classifier confidence level for the actual class, the all-pixel attacks were more successful and achieved up to an 84% average decrease in confidence, along with an 81.6% misclassification rate, in the case of the attack that we tested with the highest levels of perturbation. Even with these high levels of perturbation, the face images remained identifiable to a human. Understanding how these noised and perturbed images baffle the classification algorithms can yield valuable advances in the training of DNNs against defense-aware adversarial attacks, as well as adaptive noise reduction techniques. We hope our research may help to advance the study of adversarial attacks on DNNs and defensive mechanisms to counteract them, particularly in the facial recognition domain., Comment: 18 pages, 8 figures, fixed typos, replotted figures, restyled the plots and tables