arXiv subjects

Catherine Schuman

Publications and source records attributed to Catherine Schuman.

15 recordsLinked to original sources

arXiv2026

SuperNeuroMAT: An Efficient Matrix-based Simulator for Spiking Neural Networks

Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing. However, their widespread adoption is hindered by a lack of fast, accessible, and versatile simulation frameworks. In this paper, we introduce SuperNeuroMAT, an open-source, scalable, and highly efficient Python-based SNN simulator. We devise a novel matrix-based approach to model the leaky integrate-and-fire (LIF) neuron dynamics and natively support dense and sparse execution modes. This enables fast simulation of approximately 10,000 neurons in dense mode and 100,000 neurons in sparse mode on standard laptops and desktops without requiring specialized hardware. We demonstrate that SuperNeuroMAT consistently outperforms four established SNN simulators---NEST, Brian2, BindsNET, and snnTorch---on two performance metrics (execution speed and peak resident memory) and across various network sizes and connection probabilities. Furthermore, we demonstrate SuperNeuroMAT's applicability across a diverse set of problems. SuperNeuroMAT can efficiently handle conventional machine learning benchmarks such as the Digits and citation network datasets as well as neuromorphic event-based vision tasks such as N-CARS and ASL-DVS. Moreover, it can be extended beyond machine learning workloads and facilitate general-purpose workloads. We validated this by implementing the neuromorphic shortest path algorithm and two arithmetic primitives (addition and multiplication). SuperNeuroMAT can be installed via the Python Package Index (PyPI), thereby lowering the barrier to entry into the field of neuromorphic computing and accelerating the broader development of neuromorphic algorithms.

cs.NE↗

arXiv2025

Exploring Spiking Neural Networks for Binary Classification in Multivariate Time Series at the Edge

We present a general framework for training spiking neural networks (SNNs) to perform binary classification on multivariate time series, with a focus on step-wise prediction and high precision at low false alarm rates. The approach uses the Evolutionary Optimization of Neuromorphic Systems (EONS) algorithm to evolve sparse, stateful SNNs by jointly optimizing their architectures and parameters. Inputs are encoded into spike trains, and predictions are made by thresholding a single output neuron's spike counts. We also incorporate simple voting ensemble methods to improve performance and robustness. To evaluate the framework, we apply it with application-specific optimizations to the task of detecting low signal-to-noise ratio radioactive sources in gamma-ray spectral data. The resulting SNNs, with as few as 49 neurons and 66 synapses, achieve a 51.8% true positive rate (TPR) at a false alarm rate of 1/hr, outperforming PCA (42.7%) and deep learning (49.8%) baselines. A three-model any-vote ensemble increases TPR to 67.1% at the same false alarm rate. Hardware deployment on the microCaspian neuromorphic platform demonstrates 2mW power consumption and 20.2ms inference latency. We also demonstrate generalizability by applying the same framework, without domain-specific modification, to seizure detection in EEG recordings. An ensemble achieves 95% TPR with a 16% false positive rate, comparable to recent deep learning approaches with significant reduction in parameter count.

cs.LG↗

arXiv2025

NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. Prior neuromorphic computing benchmark efforts have not seen widespread adoption due to a lack of inclusive, actionable, and iterative benchmark design and guidelines. To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of researchers across industry and academia, aiming to provide a representative structure for standardizing the evaluation of neuromorphic approaches. The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings. In this article, we outline tasks and guidelines for benchmarks across multiple application domains, and present initial performance baselines across neuromorphic and conventional approaches for both benchmark tracks. NeuroBench is intended to continually expand its benchmarks and features to foster and track the progress made by the research community.

cs.AI↗

arXiv2025

Energy-Efficient Cryogenic Neuromorphic Network with Superconducting Memristor

Cryogenic neuromorphic systems, inspired by the brains unparalleled efficiency, present a promising paradigm for next generation computing architectures.This work introduces a fully integrated neuromorphic framework that combines superconducting memristor(SM) based spiking neurons and synapse topologies to achieve a low power neuromorphic network with non volatile synaptic strength.This neurosynaptic framework is validated by implementing the cart pole control task, a dynamic decision making problem requiring real time computation.Through detailed simulations, we demonstrate the network's ability to execute this task with an average fitness of 5965 timesteps across 1000 randomized test episodes, with 40 percent achieving the target fitness of 15,000 timesteps (0.02s per timestep).The system achieves 23 distinct spiking rates across neurons, ensuring efficient information encoding.Our findings establish the potential of SM based cryogenic neuromorphic systems to address the energy and scalability limitations of traditional computing, paving the way for biologically inspired, ultra low power computational frameworks.

cs.ET↗

arXiv2024

Exploration of Novel Neuromorphic Methodologies for Materials Applications

Many of today's most interesting questions involve understanding and interpreting complex relationships within graph-based structures. For instance, in materials science, predicting material properties often relies on analyzing the intricate network of atomic interactions. Graph neural networks (GNNs) have emerged as a popular approach for these tasks; however, they suffer from limitations such as inefficient hardware utilization and over-smoothing. Recent advancements in neuromorphic computing offer promising solutions to these challenges. In this work, we evaluate two such neuromorphic strategies known as reservoir computing and hyperdimensional computing. We compare the performance of both approaches for bandgap classification and regression using a subset of the Materials Project dataset. Our results indicate recent advances in hyperdimensional computing can be applied effectively to better represent molecular graphs.

cs.ET↗

arXiv2024

Transductive Spiking Graph Neural Networks for Loihi

Graph neural networks have emerged as a specialized branch of deep learning, designed to address problems where pairwise relations between objects are crucial. Recent advancements utilize graph convolutional neural networks to extract features within graph structures. Despite promising results, these methods face challenges in real-world applications due to sparse features, resulting in inefficient resource utilization. Recent studies draw inspiration from the mammalian brain and employ spiking neural networks to model and learn graph structures. However, these approaches are limited to traditional Von Neumann-based computing systems, which still face hardware inefficiencies. In this study, we present a fully neuromorphic implementation of spiking graph neural networks designed for Loihi 2. We optimize network parameters using Lava Bayesian Optimization, a novel hyperparameter optimization system compatible with neuromorphic computing architectures. We showcase the performance benefits of combining neuromorphic Bayesian optimization with our approach for citation graph classification using fixed-precision spiking neurons. Our results demonstrate the capability of integer-precision, Loihi 2 compatible spiking neural networks in performing citation graph classification with comparable accuracy to existing floating point implementations.

cs.ET↗

arXiv2023

Magnetic Tunnel Junction Random Number Generators Applied to Dynamically Tuned Probability Trees Driven by Spin Orbit Torque

Perpendicular magnetic tunnel junction (pMTJ)-based true-random number generators (RNG) can consume orders of magnitude less energy per bit than CMOS pseudo-RNG. Here, we numerically investigate with a macrospin Landau-Lifshitz-Gilbert equation solver the use of pMTJs driven by spin-orbit torque to directly sample numbers from arbitrary probability distributions with the help of a tunable probability tree. The tree operates by dynamically biasing sequences of pMTJ relaxation events, called 'coinflips', via an additional applied spin-transfer-torque current. Specifically, using a single, ideal pMTJ device we successfully draw integer samples on the interval 0,255 from an exponential distribution based on p-value distribution analysis. In order to investigate device-to-device variations, the thermal stability of the pMTJs are varied based on manufactured device data. It is found that while repeatedly using a varied device inhibits ability to recover the probability distribution, the device variations average out when considering the entire set of devices as a 'bucket' to agnostically draw random numbers from. Further, it is noted that the device variations most significantly impact the highest level of the probability tree, iwth diminishing errors at lower levels. The devices are then used to draw both uniformly and exponentially distributed numbers for the Monte Carlo computation of a problem from particle transport, showing excellent data fit with the analytical solution. Finally, the devices are benchmarked against CMOS and memristor RNG, showing faster bit generation and significantly lower energy use.

cond-mat.mes-hall↗

arXiv2023

Enhanced Read Resolution in Reconfigurable Memristive Synapses for Spiking Neural Networks

Synapse is a key element of any neuromorphic computing system which is mostly constructed with memristor devices. A memristor is a two-terminal analog memory device. Memristive synapse suffers from various challenges such as forming at high voltage, SET, RESET failure, and READ margin or resolution issue between two weights. Enhanced READ resolution is very important to make a memristive synapse functionally reliable. Usually, the READ resolution is very small for a memristive synapse with 4-bit data precision. This work considers a step-by-step analysis to enhance the READ current resolution for a current-controlled memristor-based synapse. An empirical model is used to characterize the HfO2-based memristive device. 1st and 2nd stage device of our proposed synapse can be scaled to enhance the READ current margin up to ~ 4.3x and ~ 21% respectively. Moreover, READ current resolution can be enhanced with run-time adaptation features such as READ voltage scaling and body biasing. The READ voltage scaling and body biasing can improve the READ current resolution by about 46% and 15% respectively. TENNLabs' neuromorphic computing framework is leveraged to evaluate the effect of READ current resolution on classification applications. Higher READ current resolution shows better accuracy than lower resolution with different percentages of read noise scenarios.

cs.ET↗

arXiv2023

Benchmarking the human brain against computational architectures

The human brain has inspired novel concepts complementary to classical and quantum computing architectures, such as artificial neural networks and neuromorphic computers, but it is not clear how their performances compare. Here we report a new methodological framework for benchmarking cognitive performance based on solving computational problems with increasing problem size. We determine computational efficiencies in experiments with human participants and benchmark these against complexity classes. We show that a neuromorphic architecture with limited field-of-view size and added noise provides a good approximation to our results. The benchmarking also suggests there is no quantum advantage on the scales of human capability compared to the neuromorphic model. Thus, the framework offers unique insights into the computational efficiency of the brain by considering it a black box.

q-bio.NC↗

arXiv2022

Random Bitstream Generation using Voltage-Controlled Magnetic Anisotropy and Spin Orbit Torque Magnetic Tunnel Junctions

Probabilistic computing using random number generators (RNGs) can leverage the inherent stochasticity of nanodevices for system-level benefits. The magnetic tunnel junction (MTJ) has been studied as an RNG due to its thermally-driven magnetization dynamics, often using spin transfer torque (STT) current amplitude to control the random switching of the MTJ free layer magnetization, here called the stochastic write method. There are additional knobs to control the MTJ-RNG, including voltage-controlled magnetic anisotropy (VCMA) and spin orbit torque (SOT), and there is need to systematically study and compared these methods. We build an analytical model of the MTJ to characterize using VCMA and SOT to generate random bit streams. The results show that both methods produce high quality, uniformly distributed bitstreams. Biasing the bitstreams using either STT current or an applied magnetic field shows an approximately sigmoidal distribution vs. bias amplitude for both VCMA and SOT, compared to less sigmoidal for stochastic write for the same conditions. The energy consumption per sample is calculated to be 0.1 pJ (SOT), 1 pJ (stochastic write), and 20 pJ (VCMA), revealing the potential energy benefit of using SOT and showing using VCMA may require higher damping materials. The generated bitstreams are then applied to two example tasks: generating an arbitrary probability distribution using the Hidden Correlation Bernoulli Coins method and using the MTJ-RNGs as stochastic neurons to perform simulated annealing in a Boltzmann machine, where both VCMA and SOT methods show the ability to effectively minimize the system energy with small delay and low energy. These results show the flexibility of the MTJ as a true RNG and elucidate design parameters for optimizing the device operation for applications.

cond-mat.mes-hall↗

arXiv2022

Biological connectomes as a representation for the architecture of artificial neural networks

Grand efforts in neuroscience are working toward mapping the connectomes of many new species, including the near completion of the Drosophila melanogaster. It is important to ask whether these models could benefit artificial intelligence. In this work we ask two fundamental questions: (1) where and when biological connectomes can provide use in machine learning, (2) which design principles are necessary for extracting a good representation of the connectome. Toward this end, we translate the motor circuit of the C. Elegans nematode into artificial neural networks at varying levels of biophysical realism and evaluate the outcome of training these networks on motor and non-motor behavioral tasks. We demonstrate that biophysical realism need not be upheld to attain the advantages of using biological circuits. We also establish that, even if the exact wiring diagram is not retained, the architectural statistics provide a valuable prior. Finally, we show that while the C. Elegans locomotion circuit provides a powerful inductive bias on locomotion problems, its structure may hinder performance on tasks unrelated to locomotion such as visual classification problems.

cs.NE↗

arXiv2022

Encoding Integers and Rationals on Neuromorphic Computers using Virtual Neuron

Neuromorphic computers perform computations by emulating the human brain, and use extremely low power. They are expected to be indispensable for energy-efficient computing in the future. While they are primarily used in spiking neural network-based machine learning applications, neuromorphic computers are known to be Turing-complete, and thus, capable of general-purpose computation. However, to fully realize their potential for general-purpose, energy-efficient computing, it is important to devise efficient mechanisms for encoding numbers. Current encoding approaches have limited applicability and may not be suitable for general-purpose computation. In this paper, we present the virtual neuron as an encoding mechanism for integers and rational numbers. We evaluate the performance of the virtual neuron on physical and simulated neuromorphic hardware and show that it can perform an addition operation using 23 nJ of energy on average using a mixed-signal memristor-based neuromorphic processor. We also demonstrate its utility by using it in some of the mu-recursive functions, which are the building blocks of general-purpose computation.

cs.NE↗

arXiv2021

Neuromorphic Computing is Turing-Complete

Neuromorphic computing is a non-von Neumann computing paradigm that performs computation by emulating the human brain. Neuromorphic systems are extremely energy-efficient and known to consume thousands of times less power than CPUs and GPUs. They have the potential to drive critical use cases such as autonomous vehicles, edge computing and internet of things in the future. For this reason, they are sought to be an indispensable part of the future computing landscape. Neuromorphic systems are mainly used for spike-based machine learning applications, although there are some non-machine learning applications in graph theory, differential equations, and spike-based simulations. These applications suggest that neuromorphic computing might be capable of general-purpose computing. However, general-purpose computability of neuromorphic computing has not been established yet. In this work, we prove that neuromorphic computing is Turing-complete and therefore capable of general-purpose computing. Specifically, we present a model of neuromorphic computing, with just two neuron parameters (threshold and leak), and two synaptic parameters (weight and delay). We devise neuromorphic circuits for computing all the μ-recursive functions (i.e., constant, successor and projection functions) and all the μ-recursive operators (i.e., composition, primitive recursion and minimization operators). Given that the μ-recursive functions and operators are precisely the ones that can be computed using a Turing machine, this work establishes the Turing-completeness of neuromorphic computing.

cs.NE↗

arXiv2020

Automated detection of corrosion in used nuclear fuel dry storage canisters using residual neural networks

Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of corrosion, including iron oxide discoloration, pitting and stress corrosion cracking, in dry storage stainless steel canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel.

cs.CV↗

arXiv2017

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

Current Deep Learning approaches have been very successful using convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers. Three limitations of this approach are: 1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; 2) the networks are manually configured to achieve optimal results, and 3) the implementation of neuron model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. We show a quantum computer can find high quality values of intra-layer connections weights, in a tractable time as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.

cs.NE↗