Search

We study the application of a neural network architecture for identifying charged particle trajectories via unsupervised learning of delays and synaptic weights using a spike-time-dependent plasticity rule. In the considered model, the neurons receive time-encoded information on the position of particle hits in a tracking detector for a particle collider, modeled according to the geometry of the Compact Muon Solenoid Phase II detector. We show how a spiking neural network is capable of successfully identifying in a completely unsupervised way the signal left by charged particles in the presence of conspicuous noise from accidental or combinatorial hits. These results open the way to applications of neuromorphic computing to particle tracking, motivating further studies into its potential for real-time, low-power particle tracking in future high-energy physics experiments., Comment: 24 pages, 21 figures, submitted to MDPI Particles

Recent advances in machine learning have opened new avenues for optimizing detector designs in high-energy physics, where the complex interplay of geometry, materials, and physics processes has traditionally posed a significant challenge. In this work, we introduce the $\textit{end-to-end}$ optimization framework AIDO that leverages a diffusion model as a surrogate for the full simulation and reconstruction chain, enabling gradient-based design exploration in both continuous and discrete parameter spaces. Although this framework is applicable to a broad range of detectors, we illustrate its power using the specific example of a sampling calorimeter, focusing on charged pions and photons as representative incident particles. Our results demonstrate that the diffusion model effectively captures critical performance metrics for calorimeter design, guiding the automatic search for layer arrangement and material composition that aligns with known calorimeter principles. The success of this proof-of-concept study provides a foundation for future applications of end-to-end optimization to more complex detector systems, offering a promising path toward systematically exploring the vast design space in next-generation experiments., Comment: 14 pages, 9 figures, submitted to MDPI particles

This research focused on utilizing ROS2 and Gazebo for simulating the TurtleBot3 robot, with the aim of exploring autonomous navigation capabilities. While the study did not achieve full autonomous navigation, it successfully established the connection between ROS2 and Gazebo and enabled manual simulation of the robot's movements. The primary objective was to understand how these tools can be integrated to support autonomous functions, providing valuable insights into the development process. The results of this work lay the groundwork for future research into autonomous robotics. The topic is particularly engaging for both teenagers and adults interested in discovering how robots function independently and the underlying technology involved. This research highlights the potential for further advancements in autonomous systems and serves as a stepping stone for more in-depth studies in the field., Comment: in Spanish language

This article presents initial configuration work and use of the robotic platform and manipulator in question. The development of the ideal configuration for using this robot serves as a guide for new users and also validates its functionality for use in projects. Husky is a large payload capacity and power systems robotics development platform that accommodates a wide variety of payloads, customized to meet research needs. Together with the Cobot UR5 Manipulator attached to its base, it expands the application area of its capacity in projects. Advances in robots and mobile manipulators have revolutionized industries by automating tasks that previously required human intervention. These innovations alone increase productivity but also reduce operating costs, which makes the company more competitive in an evolving global market. Therefore, this article investigates the functionalities of this robot to validate its execution in robotics projects., Comment: in Portuguese language

This study investigates the interaction between humanoid robots NAO and Pepper, emphasizing their potential applications in educational settings. NAO, widely used in education, and Pepper, designed for social interactions, of er new opportunities for autonomous communication and collaboration. Through a series of programmed interactions, the robots demonstrated their ability to communicate and coordinate actions autonomously, highlighting their potential as tools for enhancing learning environments. The research also explores the integration of emerging technologies, such as artificial intelligence, into these systems, allowing robots to learn from each other and adapt their behavior. The findings suggest that NAO and Pepper can significantly contribute to both technical learning and the development of social and emotional skills in students, of ering innovative pedagogical approaches through the use of humanoid robotics., Comment: in Portuguese language

The short-loading cycle is a repetitive task performed in high quantities, making it a great alternative for automation. In the short-loading cycle, an expert operator navigates towards a pile, fills the bucket with material, navigates to a dump truck, and dumps the material into the tipping body. The operator has to balance the productivity goal while minimising the fuel usage, to maximise the overall efficiency of the cycle. In addition, difficult interactions, such as the tyre-to-surface interaction further complicate the cycle. These types of hard-to-model interactions that can be difficult to address with rule-based systems, together with the efficiency requirements, motivate us to examine the potential of data-driven approaches. In this paper, the possibility of teaching an agent through reinforcement learning to approach a dump truck's tipping body and get in position to dump material in the tipping body is examined. The agent is trained in a 3D simulated environment to perform a simplified navigation task. The trained agent is directly transferred to a real vehicle, to perform the same task, with no additional training. The results indicate that the agent can successfully learn to navigate towards the dump truck with a limited amount of control signals in simulation and when transferred to a real vehicle, exhibits the correct behaviour.

This paper proposes a mini autonomous car to be used by the team UruBots for the 2024 FIRA Autonomous Cars Race Challenge. The vehicle is proposed focusing on a low cost and light weight setup. Powered by a Raspberry PI4 and with a total weight of 1.15 Kilograms, we show that our vehicle manages to race a track of approximately 13 meters in 11 seconds at the best evaluation that was carried out, with an average speed of 1.2m/s in average. That performance was achieved after training a convolutional neural network with 1500 samples for a total amount of 60 epochs. Overall, we believe that our vehicle are suited to perform at the FIRA Autonomous Cars Race Challenge 2024, helping the development of the field of study and the category in the competition., Comment: Team Description Paper for the FIRA RoboWorld Cup 2024

The goal of this paper is to provide a methodology to prove existence of (fiberwise hyperbolic) real-analytic invariant tori in real-analytic quasi-periodic skew-product dynamical systems that present nearly-invariant tori of the same characteristics. The methodology is based on the application of a Newton-Kantorovich theorem whose hypotheses are tested using Fourier analysis methods for a numerical approximation of the parameterization of an invariant torus.

In this paper we discuss the design and implementation of a plasma display panel for a wide field of view desktop virtual reality environment. Present commercial plasma displays are not designed with virtual reality in mind, leading to several problems in generating stereo imagery and obtaining good tracking information. Although we developed solutions for a number of these problems, the limitations of the system preclude its current use in practical applications, and point to issues that must be resolved for flat panel displays to be useful for VR., Comment: 6 pages, 5 figures, 3rd International Immersive Projection Technology Workshop (Stuttgart, Germany, 10-11 May 1999)

We present a collection of heuristics and simple tests for evaluating the quality of a projection-based virtual reality display. A typical VR system includes numerous potential sources of error. By understanding the characteristics of a correctly working system, and the types of errors that are likely to occur, users can quickly determine if their display is inaccurate and what components may need correction., Comment: 7 pages, 6 figures, 4th International Immersive Projection Technology Workshop (Ames, Iowa, 19-20 June 2000)

In this article we examine recent developments in the research area concerning the creation of end-to-end models for the complete optimization of measuring instruments. The models we consider rely on differentiable programming methods and on the specification of a software pipeline including all factors impacting performance -- from the data-generating processes to their reconstruction and the extraction of inference on the parameters of interest of a measuring instrument -- along with the careful specification of a utility function well aligned with the end goals of the experiment. Building on previous studies originated within the MODE Collaboration, we focus specifically on applications involving instruments for particle physics experimentation, as well as industrial and medical applications that share the detection of radiation as their data-generating mechanism., Comment: 70 pages, 17 figures. To be submitted to journal

We replace the multiplication and sigmoid function of the conventional recurrent gate with addition and ReLU activation. This mechanism is designed to maintain long-term memory for sequence processing but at a reduced computational cost, thereby opening up for more efficient execution or larger models on restricted hardware. Recurrent Neural Networks (RNNs) with gating mechanisms such as LSTM and GRU have been widely successful in learning from sequential data due to their ability to capture long-term dependencies. Conventionally, the update based on current inputs and the previous state history is each multiplied with dynamic weights and combined to compute the next state. However, multiplication can be computationally expensive, especially for certain hardware architectures or alternative arithmetic systems such as homomorphic encryption. It is demonstrated that the novel gating mechanism can capture long-term dependencies for a standard synthetic sequence learning task while significantly reducing computational costs such that execution time is reduced by half on CPU and by one-third under encryption. Experimental results on handwritten text recognition tasks furthermore show that the proposed architecture can be trained to achieve comparable accuracy to conventional GRU and LSTM baselines. The gating mechanism introduced in this paper may enable privacy-preserving AI applications operating under homomorphic encryption by avoiding the multiplication of encrypted variables. It can also support quantization in (unencrypted) plaintext applications, with the potential for substantial performance gains since the addition-based formulation can avoid the expansion to double precision often required for multiplication., Comment: 12 pages, 4 tables

The concept of image similarity is ambiguous, and images can be similar in one context and not in another. This ambiguity motivates the creation of metrics for specific contexts. This work explores the ability of deep perceptual similarity (DPS) metrics to adapt to a given context. DPS metrics use the deep features of neural networks for comparing images. These metrics have been successful on datasets that leverage the average human perception in limited settings. But the question remains if they could be adapted to specific similarity contexts. No single metric can suit all similarity contexts, and previous rule-based metrics are labor-intensive to rewrite for new contexts. On the other hand, DPS metrics use neural networks that might be retrained for each context. However, retraining networks takes resources and might ruin performance on previous tasks. This work examines the adaptability of DPS metrics by training ImageNet pretrained CNNs to measure similarity according to given contexts. Contexts are created by randomly ranking six image distortions. Distortions later in the ranking are considered more disruptive to similarity when applied to an image for that context. This also gives insight into whether the pretrained features capture different similarity contexts. The adapted metrics are evaluated on a perceptual similarity dataset to evaluate if adapting to a ranking affects their prior performance. The findings show that DPS metrics can be adapted with high performance. While the adapted metrics have difficulties with the same contexts as baselines, performance is improved in 99% of cases. Finally, it is shown that the adaption is not significantly detrimental to prior performance on perceptual similarity. The implementation of this work is available online: https://github.com/LTU-Machine-Learning/Analysis-of-Deep-Perceptual-Loss-Networks

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss function for images that computes the error between two images as the distance between deep features extracted from a neural network. Most applications of the loss use pretrained networks called loss networks for deep feature extraction. However, despite increasingly widespread use, the effects of loss network implementation on the trained models have not been studied. This work rectifies this through a systematic evaluation of the effect of different pretrained loss networks on four different application areas. Specifically, the work evaluates 14 different pretrained architectures with four different feature extraction layers. The evaluation reveals that VGG networks without batch normalization have the best performance and that the choice of feature extraction layer is at least as important as the choice of architecture. The analysis also reveals that deep perceptual loss does not adhere to the transfer learning conventions that better ImageNet accuracy implies better downstream performance and that feature extraction from the later layers provides better performance.

With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition. One promising approach is the use of neuromorphic sensors and spiking neural networks (SNNs) implemented in neuromorphic processors for sparse event-driven sensing. However, this requires resource-efficient SNN mechanisms for temporal encoding, which need to consider that these systems process information in a streaming manner, with physical time being an intrinsic property of their operation. In this work, two candidate neurocomputational elements for temporal encoding and feature extraction in SNNs described in recent literature - the spiking time-difference encoder (TDE) and disynaptic excitatory-inhibitory (E-I) elements - are comparatively investigated in a keyword-spotting task on formants computed from spoken digits in the TIDIGITS dataset. While both encoders improve performance over direct classification of the formant features in the training data, enabling a complete binary classification with a logistic regression model, they show no clear improvements on the test set. Resource-efficient keyword spotting applications may benefit from the use of these encoders, but further work on methods for learning the time constants and weights is required to investigate their full potential., Comment: This work has been submitted to the IEEE for possible publication

Stellar winds of cool and pulsating asymptotic giant branch (AGB) stars enrich the interstellar medium with large amounts of processed elements and various types of dust. We present the first study on the influence of gas-to-dust drift on ab initio simulations of stellar winds of M-type stars driven by radiation pressure on forsterite particles. Our study is based on our radiation hydrodynamic model code T-800 that includes frequency-dependent radiative transfer, dust extinction based on Mie scattering, grain growth and ablation, gas-to-dust drift using one mean grain size, a piston that simulates stellar pulsations, and an accurate high spatial resolution numerical scheme. To enable this study, we calculated new gas opacities based on the ExoMol database, and we extended the model code to handle the formation of minerals that may form in M-type stars. We determine the effects of drift by comparing drift models to our new and extant non-drift models. Three out of four new drift models show high drift velocities, 87-310 km/s. Our new drift model mass-loss rates are 1.7-13 per cent of the corresponding values of our non-drift models, but compared to the results of two extant non-drift models that use the same stellar parameters, these same values are 0.33-1.5 per cent. Meanwhile, a comparison of other properties such as the expansion velocity and grain size show similar values. Our results, which are based on single-component forsterite particles, show that the inclusion of gas-to-drift is of fundamental importance in stellar wind models driven by such transparent grains. Assuming that the drift velocity is insignificant, properties such as the mass-loss rate may be off from more realistic values by a factor of 50 or more., Comment: 15 pages, 6 figures, accepted and in press

Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource requirements of digital computing and deep learning are growing exponentially, in an unsustainable manner. One possible way to bridge this gap is the adoption of resource-efficient brain-inspired "neuromorphic" processing and sensing devices, which use event-driven, asynchronous, dynamic neurosynaptic elements with colocated memory for distributed processing and machine learning. However, since neuromorphic systems are fundamentally different from conventional von Neumann computers and clock-driven sensor systems, several challenges are posed to large-scale adoption and integration of neuromorphic devices into the existing distributed digital-computational infrastructure. Here, we describe the current landscape of neuromorphic computing, focusing on characteristics that pose integration challenges. Based on this analysis, we propose a microservice-based framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which provides virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction. We also present concepts that could serve as a basis for the realization of this framework, and identify directions for further research required to enable large-scale system integration of neuromorphic devices.

Measuring the similarity of images is a fundamental problem to computer vision for which no universal solution exists. While simple metrics such as the pixel-wise L2-norm have been shown to have significant flaws, they remain popular. One group of recent state-of-the-art metrics that mitigates some of those flaws are Deep Perceptual Similarity (DPS) metrics, where the similarity is evaluated as the distance in the deep features of neural networks. However, DPS metrics themselves have been less thoroughly examined for their benefits and, especially, their flaws. This work investigates the most common DPS metric, where deep features are compared by spatial position, along with metrics comparing the averaged and sorted deep features. The metrics are analyzed in-depth to understand the strengths and weaknesses of the metrics by using images designed specifically to challenge them. This work contributes with new insights into the flaws of DPS, and further suggests improvements to the metrics. An implementation of this work is available online: https://github.com/guspih/deep_perceptual_similarity_analysis/