Search

Neural networks (NN) can be divided into two broad categories, recurrent and non-recurrent. Both types of neural networks are popular and extensively studied, but they are often treated as distinct families of machine learning algorithms. In this position paper, we argue that there is a closer relationship between these two types of neural networks than is normally appreciated. We show that many common neural network models, such as Recurrent Neural Networks (RNN), Multi-Layer Perceptrons (MLP), and even deep multi-layer transformers, can all be represented as iterative maps. The close relationship between RNNs and other types of NNs should not be surprising. In particular, RNNs are known to be Turing complete, and therefore capable of representing any computable function (such as any other types of NNs), but herein we argue that the relationship runs deeper and is more practical than this. For example, RNNs are often thought to be more difficult to train than other types of NNs, with RNNs being plagued by issues such as vanishing or exploding gradients. However, as we demonstrate in this paper, MLPs, RNNs, and many other NNs lie on a continuum, and this perspective leads to several insights that illuminate both theoretical and practical aspects of NNs.

Multivariate time series data are ubiquitous in the application of machine learning to problems in the physical sciences. Chemiresistive sensor arrays are highly promising in chemical detection tasks relevant to industrial, safety, and military applications. Sensor arrays are an inherently multivariate time series data collection tool which demand rapid and accurate classification of arbitrary chemical analytes. Previous research has benchmarked data-agnostic multivariate time series classifiers across diverse multivariate time series supervised tasks in order to find general-purpose classification algorithms. To our knowledge, there has yet to be an effort to survey machine learning and time series classification approaches to chemiresistive hardware sensor arrays for the detection of chemical analytes. In addition to benchmarking existing approaches to multivariate time series classifiers, we incorporate findings from a model survey to propose the novel \textit{ChemTime} approach to sensor array classification for chemical sensing. We design experiments addressing the unique challenges of hardware sensor arrays classification including the rapid classification ability of classifiers and minimization of inference time while maintaining performance for deployed lightweight hardware sensing devices. We find that \textit{ChemTime} is uniquely positioned for the chemical sensing task by combining rapid and early classification of time series with beneficial inference and high accuracy., Comment: 14 pages, 12 figures

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph's topology, particularly for large-scale or complex graphs. We propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current practice. Experimental results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning., Comment: This paper is submitted and will be published on Big Data Conference 2023, Data-driven Science for Graphs: Algorithms, Architectures, and Application workshop

Accurate chemical sensors are vital in medical, military, and home safety applications. Training machine learning models to be accurate on real world chemical sensor data requires performing many diverse, costly experiments in controlled laboratory settings to create a data set. In practice even expensive, large data sets may be insufficient for generalization of a trained model to a real-world testing distribution. Rather than perform greater numbers of experiments requiring exhaustive mixtures of chemical analytes, this research proposes learning approximations of complex exposures from training sets of simple ones by using single-analyte exposure signals as building blocks of a multiple-analyte space. We demonstrate this approach to synthetic sensor responses surprisingly improves the detection of out-of-distribution obscured chemical analytes. Further, we pair these synthetic signals to targets in an information-dense representation space utilizing a large corpus of chemistry knowledge. Through utilization of a semantically meaningful analyte representation spaces along with synthetic targets we achieve rapid analyte classification in the presence of obscurants without corresponding obscured-analyte training data. Transfer learning for supervised learning with molecular representations makes assumptions about the input data. Instead, we borrow from the natural language and natural image processing literature for a novel approach to chemical sensor signal classification using molecular semantics for arbitrary chemical sensor hardware designs., Comment: 12 pages, 14 figures

Traditional frequency based projection filters, or projection operators (PO), separate signal and noise through a series of transformations which remove frequencies where noise is present. However, this technique relies on a priori knowledge of what frequencies contain signal and noise and that these frequencies do not overlap, which is difficult to achieve in practice. To address these issues, we introduce a PO-neural network hybrid model, the Pseudo Projection Operator (PPO), which leverages a neural network to perform frequency selection. We compare the filtering capabilities of a PPO, PO, and denoising autoencoder (DAE) on the University of Rochester Multi-Modal Music Performance Dataset with a variety of added noise types. In the majority of experiments, the PPO outperforms both the PO and DAE. Based upon these results, we suggest future application of the PPO to filtering problems in the physical and biological sciences.

Learning dynamics of collectively moving agents such as fish or humans is an active field in research. Due to natural phenomena such as occlusion and change of illumination, the multi-object methods tracking such dynamics might lose track of the agents where that might result fragmentation in the constructed trajectories. Here, we present an extended deep autoencoder (DA) that we train only on fully observed segments of the trajectories by defining its loss function as the Hadamard product of a binary indicator matrix with the absolute difference between the outputs and the labels. The trajectories of the agents practicing collective motion is low-rank due to mutual interactions and dependencies between the agents that we utilize as the underlying pattern that our Hadamard deep autoencoder (HDA) codes during its training. The performance of our HDA is compared with that of a low-rank matrix completion scheme in the context of fragmented trajectory reconstruction., Comment: 21 Pages, 5 figures, submitted into Pattern Recognition

Ensemble learning is a process by which multiple base learners are strategically generated and combined into one composite learner. There are two features that are essential to an ensemble's performance, the individual accuracies of the component learners and the overall diversity in the ensemble. The right balance of learner accuracy and ensemble diversity can improve the performance of machine learning tasks on benchmark and real-world data sets, and recent theoretical and practical work has demonstrated the subtle trade-off between accuracy and diversity in an ensemble. In this paper, we extend the extant literature by providing a deeper theoretical understanding for assessing and improving the optimality of any given ensemble, including random forests and deep neural network ensembles. We also propose a training algorithm for neural network ensembles and demonstrate that our approach provides improved performance when compared to both state-of-the-art individual learners and ensembles of state-of-the-art learners trained using standard loss functions. Our key insight is that it is better to explicitly encourage diversity in an ensemble, rather than merely allowing diversity to occur by happenstance, and that rigorous theoretical bounds on the trade-off between diversity and learner accuracy allow one to know when an optimal arrangement has been achieved.

In this paper, we propose a novel method to make distance predictions in real-world social networks. As predicting missing distances is a difficult problem, we take a two-stage approach. Structural parameters for families of synthetic networks are first estimated from a small set of measurements of a real-world network and these synthetic networks are then used to pre-train the predictive neural networks. Since our model first searches for the most suitable synthetic graph parameters which can be used as an "oracle" to create arbitrarily large training data sets, we call our approach "Oracle Search Pre-training" (OSP). For example, many real-world networks exhibit a Power law structure in their node degree distribution, so a Power law model can provide a foundation for the desired oracle to generate synthetic pre-training networks, if the appropriate Power law graph parameters can be estimated. Accordingly, we conduct experiments on real-world Facebook, Email, and Train Bombing networks and show that OSP outperforms models without pre-training, models pre-trained with inaccurate parameters, and other distance prediction schemes such as Low-rank Matrix Completion. In particular, we achieve a prediction error of less than one hop with only 1% of sampled distances from the social network. OSP can be easily extended to other domains such as random networks by choosing an appropriate model to generate synthetic training data, and therefore promises to impact many different network learning problems., Comment: KDD conference 2021

In this paper, we demonstrate how deep autoencoders can be generalized to the case of inpainting and denoising, even when no clean training data is available. In particular, we show how neural networks can be trained to perform all of these tasks simultaneously. While, deep autoencoders implemented by way of neural networks have demonstrated potential for denoising and anomaly detection, standard autoencoders have the drawback that they require access to clean data for training. However, recent work in Robust Deep Autoencoders (RDAEs) shows how autoencoders can be trained to eliminate outliers and noise in a dataset without access to any clean training data. Inspired by this work, we extend RDAEs to the case where data are not only noisy and have outliers, but also only partially observed. Moreover, the dataset we train the neural network on has the properties that all entries have noise, some entries are corrupted by large mistakes, and many entries are not even known. Given such an algorithm, many standard tasks, such as denoising, image inpainting, and unobserved entry imputation can all be accomplished simultaneously within the same framework. Herein we demonstrate these techniques on standard machine learning tasks, such as image inpainting and denoising for the MNIST and CIFAR10 datasets. However, these approaches are not only applicable to image processing problems, but also have wide ranging impacts on datasets arising from real-world problems, such as manufacturing and network processing, where noisy, partially observed data naturally arise.

LiDAR point clouds contain measurements of complicated natural scenes and can be used to update digital elevation models, glacial monitoring, detecting faults and measuring uplift detecting, forest inventory, detect shoreline and beach volume changes, landslide risk analysis, habitat mapping, and urban development, among others. A very important application is the classification of the 3D cloud into elementary classes. For example, it can be used to differentiate between vegetation, man-made structures, and water. Our goal is to present a preliminary comparison study for the classification of 3D point cloud LiDAR data that includes several types of feature engineering. In particular, we demonstrate that providing context by augmenting each point in the LiDAR point cloud with information about its neighboring points can improve the performance of downstream learning algorithms. We also experiment with several dimension reduction strategies, ranging from Principal Component Analysis (PCA) to neural network-based auto-encoders, and demonstrate how they affect classification performance in LiDAR point clouds. For instance, we observe that combining feature engineering with a dimension reduction a method such as PCA, there is an improvement in the accuracy of the classification with respect to doing a straightforward classification with the raw data., Comment: 21 pages, 12 figures

Nonlinear dimensionality reduction or, equivalently, the approximation of high-dimensional data using a low-dimensional nonlinear manifold is an active area of research. In this paper, we will present a thematically different approach to detect the existence of a low-dimensional manifold of a given dimension that lies within a set of bounds derived from a given point cloud. A matrix representing the appropriately defined distances on a low-dimensional manifold is low-rank, and our method is based on current techniques for recovering a partially observed matrix from a small set of fully observed entries that can be implemented as a low-rank Matrix Completion (MC) problem. MC methods are currently used to solve challenging real-world problems, such as image inpainting and recommender systems, and we leverage extent efficient optimization techniques that use a nuclear norm convex relaxation as a surrogate for non-convex and discontinuous rank minimization. Our proposed method provides several advantages over current nonlinear dimensionality reduction techniques, with the two most important being theoretical guarantees on the detection of low-dimensional embeddings and robustness to non-uniformity in the sampling of the manifold. We validate the performance of this approach using both a theoretical analysis as well as synthetic and real-world benchmark datasets., Comment: 12 pages, 7 figures, submitted to Pattern Recognition Journal

Dimension Estimation (DE) and Dimension Reduction (DR) are two closely related topics, but with quite different goals. In DE, one attempts to estimate the intrinsic dimensionality or number of latent variables in a set of measurements of a random vector. However, in DR, one attempts to project a random vector, either linearly or non-linearly, to a lower dimensional space that preserves the information contained in the original higher dimensional space. Of course, these two ideas are quite closely linked since, for example, doing DR to a dimension smaller than suggested by DE will likely lead to information loss. Accordingly, in this paper we will focus on a particular class of deep neural networks called autoencoders which are used extensively for DR but are less well studied for DE. We show that several important questions arise when using autoencoders for DE, above and beyond those that arise for more classic DR/DE techniques such as Principal Component Analysis. We address autoencoder architectural choices and regularization techniques that allow one to transform autoencoder latent layer representations into estimates of intrinsic dimension., Comment: 11 pages

Anomalies and outliers are common in real-world data, and they can arise from many sources, such as sensor faults. Accordingly, anomaly detection is important both for analyzing the anomalies themselves and for cleaning the data for further analysis of its ambient structure. Nonetheless, a precise definition of anomalies is important for automated detection and herein we approach such problems from the perspective of detecting sparse latent effects embedded in large collections of noisy data. Standard Graphical Lasso-based techniques can identify the conditional dependency structure of a collection of random variables based on their sample covariance matrix. However, classic Graphical Lasso is sensitive to outliers in the sample covariance matrix. In particular, several outliers in a sample covariance matrix can destroy the sparsity of its inverse. Accordingly, we propose a novel optimization problem that is similar in spirit to Robust Principal Component Analysis (RPCA) and splits the sample covariance matrix $M$ into two parts, $M=F+S$, where $F$ is the cleaned sample covariance whose inverse is sparse and computable by Graphical Lasso, and $S$ contains the outliers in $M$. We accomplish this decomposition by adding an additional $ \ell_1$ penalty to classic Graphical Lasso, and name it "Robust Graphical Lasso (Rglasso)". Moreover, we propose an Alternating Direction Method of Multipliers (ADMM) solution to the optimization problem which scales to large numbers of unknowns. We evaluate our algorithm on both real and synthetic datasets, obtaining interpretable results and outperforming the standard robust Minimum Covariance Determinant (MCD) method and Robust Principal Component Analysis (RPCA) regarding both accuracy and speed.

For many important network types (e.g., sensor networks in complex harsh environments and social networks) physical coordinate systems (e.g., Cartesian), and physical distances (e.g., Euclidean), are either difficult to discern or inapplicable. Accordingly, coordinate systems and characterizations based on hop-distance measurements, such as Topology Preserving Maps (TPMs) and Virtual-Coordinate (VC) systems are attractive alternatives to Cartesian coordinates for many network algorithms. Herein, we present an approach to recover geometric and topological properties of a network with a small set of distance measurements. In particular, our approach is a combination of shortest path (often called geodesic) recovery concepts and low-rank matrix completion, generalized to the case of hop-distances in graphs. Results for sensor networks embedded in 2-D and 3-D spaces, as well as a social networks, indicates that the method can accurately capture the network connectivity with a small set of measurements. TPM generation can now also be based on various context appropriate measurements or VC systems, as long as they characterize different nodes by distances to small sets of random nodes (instead of a set of global anchors). The proposed method is a significant generalization that allows the topology to be extracted from a random set of graph shortest paths, making it applicable in contexts such as social networks where VC generation may not be possible., Comment: 17 pages, 9 figures. arXiv admin note: substantial text overlap with arXiv:1712.10063

This paper uses network packet capture data to demonstrate how Robust Principal Component Analysis (RPCA) can be used in a new way to detect anomalies which serve as cyber-network attack indicators. The approach requires only a few parameters to be learned using partitioned training data and shows promise of ameliorating the need for an exhaustive set of examples of different types of network attacks. For Lincoln Lab's DARPA intrusion detection data set, the method achieves low false-positive rates while maintaining reasonable true-positive rates on individual packets. In addition, the method correctly detected packet streams in which an attack which was not previously encountered, or trained on, appears., Comment: 10 pages, 8 figures

For many important network types (e.g., sensor networks in complex harsh environments and social networks) physical coordinate systems (e.g., Cartesian), and physical distances (e.g., Euclidean), are either difficult to discern or inappropriate. Accordingly, Topology Preserving Maps (TPMs) derived from a Virtual-Coordinate (VC) system representing the distance to a small set of anchors is an attractive alternative to physical coordinates for many network algorithms. Herein, we present an approach, based on the theory of low-rank matrix completion, to recover geometric properties of a network with only partial information about the VCs of nodes. In particular, our approach is a combination of geodesic recovery concepts and low-rank matrix completion, generalized to the case of hop-distances in graphs. Distortion evaluated using the change of distance among node pairs shows that even with up to 40% to 60% of random coordinates missing, accurate TPMs can be obtained. TPM generation can now also be based on different context appropriate VC systems or measurements as long as they characterize each node with distances to a small set of random nodes (instead of a global set of anchors). The proposed method is a significant generalization that allows the topology to be extracted from a random set of graph geodesics, making it applicable in contexts such as social networks where VC generation may not be possible., Comment: A more recent version uploaded

Existing dimensionality reduction methods are adept at revealing hidden underlying manifolds arising from high-dimensional data and thereby producing a low-dimensional representation. However, the smoothness of the manifolds produced by classic techniques over sparse and noisy data is not guaranteed. In fact, the embedding generated using such data may distort the geometry of the manifold and thereby produce an unfaithful embedding. Herein, we propose a framework for nonlinear dimensionality reduction that generates a manifold in terms of smooth geodesics that is designed to treat problems in which manifold measurements are either sparse or corrupted by noise. Our method generates a network structure for given high-dimensional data using a nearest neighbors search and then produces piecewise linear shortest paths that are defined as geodesics. Then, we fit points in each geodesic by a smoothing spline to emphasize the smoothness. The robustness of this approach for sparse and noisy datasets is demonstrated by the implementation of the method on synthetic and real-world datasets., Comment: 13 pages, 7 figures, submitted to Pattern Recognition