Search

This paper presents a novel approach to in situ memristive learning by training spiking neural networks (SNNs) entirely within the circuit using memristor emulators in SPICE. The circuit models neurons using Lapicque neurons and employs pulse-based spike encoding to simulate spike-timing-dependent plasticity (STDP), a key learning mechanism in SNNs. The Lapicque neuron model operates according to the Leaky Integrate-and-Fire (LIF) model, which is used in this study to model spiking behavior in memristor-based SNNs. More exactly, the first memristor emulator in PySpice, a Python library for circuit simulation, was developed and integrated into a memristive circuit capable of in situ learning, named the "In Situ Memristive Learning Method for Pattern Classification". This novel technique enables time-based computation, where neurons accumulate incoming spikes and fire once a threshold is reached, mimicking biological neuron behavior. The proposed method was rigorously tested on three diverse datasets: XPUE, a custom non-dominating 3 × 3 image dataset; a 3 × 5 digit dataset ranging from 0 to 5; and a resized 10 × 10 version of the Modified National Institute of Standards and Technology (MNIST) dataset. The neuromorphic circuit achieved successful pattern learning across all three datasets, outperforming comparable results from other in situ training simulations on SPICE. The learning process harnesses the cumulative effect of memristors, enabling the network to learn a representative pattern for each label efficiently. This advancement opens new avenues for neuromorphic computing and paves the way for developing autonomous, adaptable pattern classification neuromorphic circuits. [ABSTRACT FROM AUTHOR]

Spiking Neural Networks have gained significant attention due to their potential for energy efficiency and biological plausibility. However, the reduced number of user-friendly tools for designing, training, and visualizing Spiking Neural Networks hinders widespread adoption. This paper presents the SNNtrainer3D v1.0.0, a novel software application that addresses these challenges. The application provides an intuitive interface for designing Spiking Neural Networks architectures, with features such as dynamic architecture editing, allowing users to add, remove, and edit hidden layers in real-time. A key innovation is the integration of Three.js for three-dimensional visualization of the network structure, enabling users to inspect connections and weights and facilitating a deeper understanding of the model's behavior. The application supports training on the Modified National Institute of Standards and Technology dataset and allows the downloading of trained weights for further use. Moreover, it lays the groundwork for future integration with physical memristor technology, positioning it as a crucial tool for advancing neuromorphic computing research. The advantages of the development process, technology stack, and visualization are discussed. The SNNtrainer3D represents a significant step in making Spiking Neural Networks more accessible, understandable, and easier for Artificial Intelligence researchers and practitioners. [ABSTRACT FROM AUTHOR]

It can be calculated from the respective widths I w i SB 1 sb and I w i SB 2 sb of actors I A i SB 1 sb and I A i SB 2 sb as HT ht . The inadequacy described for the DST in case (c), i.e., the case that the vehicle in front is traveling faster than the vehicle behind, is not an issue for the I a i SB long,req sb metric thanks to its abstract definition: in this particular case, the following vehicle may still accelerate (at least for a short moment), and the inequality HT ht has a positive solution I a i SB 1 sb > 0. Assuming that the path and deviation probabilities are independent, the actual position HT ht can be computed for each time interval and agent, enabling us to compute the probability of crashes by summing up all the probabilities for cases where the vehicle bodies overlap. [Extracted from the article]

This paper presents a mathematical analysis of several criticality metrics used for evaluating the safety of autonomous vehicles (AVs) and also proposes novel environmentally-friendly metrics with the scope of facilitating their selection by future researchers who want to evaluate both safety and the environmental impact of AVs. Regarding this, first, we investigate whether the criticality metrics which are used to quantify the severeness of critical situations in autonomous driving are well-defined and work as intended. In some cases, the well-definedness or the intendedness of the metrics will be apparent, but in other cases, we will present mathematical demonstrations of these properties as well as alternative novel formulas. Additionally, we also present details regarding optimality. Secondly, we propose several novel environmentally-friendly metrics as well as a novel environmentally-friendly criticality metric that combines the safety and environmental impact in a car-following scenario. Third, we discuss the possibility of applying these criticality metrics in artificial intelligence (AI) training such as reinforcement learning (RL) where they can be used as penalty terms such as negative reward components. Finally, we propose a way to apply some of the metrics in a simple car-following scenario and show in our simulation that AVs powered by petrol emitted the most carbon emissions (54.92 g of CO2), being followed closely by diesel-powered AVs (54.67 g of CO2) and then by grid-electricity-powered AVs (31.16 g of CO2). Meanwhile, the AVs powered by electricity from a green source, such as solar energy, had 0 g of CO2 emissions, encouraging future researchers and the industry to develop more actively sustainable methods and metrics for powering and evaluating the safety and environmental impact of AVs using green energy. [ABSTRACT FROM AUTHOR]

This paper presents a modified global energy production computation formula that replaces the traditional Performance Ratio (PR) with a novel Solar Reliability Factor (SRF) for mobile solar tracking systems. The SRF parameter describes the reliability and availability of a dual-axis solar tracker, which powers a smart home automation system entirely by using clean energy. By applying the SRF in the global energy production formula of solar tracking systems, we can predict the energy generation in real time, allowing proper energy management of the entire smart home automation system. Regarding static deployed Photovoltaic (PV) systems, the PR factor is preserved to compute the power generation of these devices accurately. Experimental results show that the energy production computation constantly fluctuates over several days due to the SRF parameter variation, showing a 26.11% reduction when the dual-axis solar tracker's availability is affected by system errors and maximum power generation when the solar tracking device is operating in optimal conditions. [ABSTRACT FROM AUTHOR]

This paper presents an improved mathematical model for calculating the solar test factor (STF) and solar reliability factor (SRF) of a photovoltaic (PV) automated equipment. By employing a unified metrics system and a combined testing suite encompassing various energy-efficient testing techniques, the aim of this paper is to determine a general fault coverage and improve the global SRF of a closed-loop dual-axis solar tracking system. Accelerated testing coupled with reliability analysis are essential tools for assessing the performance of modern solar tracking devices since PV system malfunctioning is directly connected to economic loss, which is an important aspect for the solar energy domain. The experimental results show that the unified metrics system is potentially suitable for assessing the reliability evaluation of many types of solar tracking systems. Additionally, the proposed combined testing platform proves efficient regarding fault coverage (overall coverage of 66.35% for all test scenarios), test time (an average of 275 min for 2864 test cycles), and power consumption (zero costs regarding electricity consumption for all considered test cases) points of view. [ABSTRACT FROM AUTHOR]

This paper presents a mathematical approach for determining the reliability of solar tracking systems based on three fault coverage-aware metrics which use system error data from hardware, software as well as in-circuit testing (ICT) techniques, to calculate a solar test factor (STF). Using Euler's named constant, the solar reliability factor (SRF) is computed to define the robustness and availability of modern, high-performance solar tracking systems. The experimental cases which were run in the Mathcad software suite and the Python programming environment show that the fault coverage-aware metrics greatly change the test and reliability factor curve of solar tracking systems, achieving significantly reduced calculation steps and computation time. [ABSTRACT FROM AUTHOR]