William Severa
YOU?
Author Swipe
View article: Advantages of imperfect dice rolls over coin flips for random number generation
Advantages of imperfect dice rolls over coin flips for random number generation Open
With an eye toward neural-inspired probabilistic computation, recent work has examined the development of true random number generators via stochastic devices. Typically, these devices are operated in a two-state regime to produce a sequen…
View article: The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning
The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning Open
Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). However, to extend SNNs to a…
View article: Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks
Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks Open
A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. T…
View article: Neuromorphic Co-Design as a Game
Neuromorphic Co-Design as a Game Open
Co-design is a prominent topic presently in computing, speaking to the mutual benefit of coordinating design choices of several layers in the technology stack. For example, this may be designing algorithms which can most efficiently take a…
View article: Synaptic Sampling of Neural Networks
Synaptic Sampling of Neural Networks Open
Probabilistic artificial neural networks offer intriguing prospects for enabling the uncertainty of artificial intelligence methods to be described explicitly in their function; however, the development of techniques that quantify uncertai…
View article: Spiking retina microscope
Spiking retina microscope Open
A spiking retina microscope comprising microscope optics and a neuromorphic imaging sensor. The microscope optics are configured to direct a magnified image of a specimen onto the neuromorphic imaging sensor. The neuromorphic imaging senso…
View article: Induced Distributions from Generalized Unfair Dice
Induced Distributions from Generalized Unfair Dice Open
In this paper we analyze the probability distributions associated with rolling (possibly unfair) dice infinitely often. Specifically, given a $q$-sided die, if $x_i\in\{0,\ldots,q-1\}$ denotes the outcome of the $i^{\text{th}}$ toss, then …
View article: Neuromorphic Population Evaluation using the Fugu Framework
Neuromorphic Population Evaluation using the Fugu Framework Open
Evolutionary algorithms have been shown to be an effective method for training (or configuring) spiking neural networks. There are, however, challenges to developing accessible, scalable, and portable solutions. We present an extension to …
View article: Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a density method
Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a density method Open
A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among diff…
View article: Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a particle method
Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a particle method Open
A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among diff…
View article: NeuralRW-Loihi: Spiking Discrete Time Markov Chain Simulator for Intel Loihi v
NeuralRW-Loihi: Spiking Discrete Time Markov Chain Simulator for Intel Loihi v Open
SAND2024-01302O NeuralRW-Loihi: Spiking Discrete Time Markov Chain Simulator for Intel Loihi is a neuromorphic script that generates a random walk simulation of a discrete-time Markov Chain for the Loihi neuromorphic hardware. The code was…
View article: SEEK: Scoping neuromorphic architecture impact enabling advanced sensing capabilities
SEEK: Scoping neuromorphic architecture impact enabling advanced sensing capabilities Open
Many sensor modalities used for proliferation detection are expanding hyperspectrally, hyperspatially, and hypertemporally. While these assets are often tasked with high-consequence image processing tasks, the significant computational cos…
View article: Stochastic Neuromorphic Circuits for Solving MAXCUT
Stochastic Neuromorphic Circuits for Solving MAXCUT Open
Finding the maximum cut of a graph (MAXCUT) is a classic optimization problem that has motivated parallel algorithm development. While approximate algorithms to MAXCUT offer attractive theoretical guarantees and demonstrate compelling empi…
View article: A review of non-cognitive applications for neuromorphic computing
A review of non-cognitive applications for neuromorphic computing Open
Though neuromorphic computers have typically targeted applications in machine learning and neuroscience (‘cognitive’ applications), they have many computational characteristics that are attractive for a wide variety of computational proble…
View article: Learning to Parameterize a Stochastic Process Using Neuromorphic Data Generation
Learning to Parameterize a Stochastic Process Using Neuromorphic Data Generation Open
Deep learning is consistently becoming more integrated into scientific computing workflows. These high-performance methods allow for data-driven discoveries enabling, among other tasks, classification, feature extraction, and regression. I…
View article: Exploring SAR ATR with neural networks: going beyond accuracy
Exploring SAR ATR with neural networks: going beyond accuracy Open
Deep neural networks have recently demonstrated state-of-the-art accuracy on public Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) benchmark datasets. While attaining competitive accuracy on benchmark datasets is a neces…
View article: Neural Mini-Apps as a Tool for Neuromorphic Computing Insight
Neural Mini-Apps as a Tool for Neuromorphic Computing Insight Open
Neuromorphic computing (NMC) is an exciting paradigm seeking to incorporate principles from biological brains to enable advanced computing capabilities. Not only does this encompass algorithms, such as neural networks, but also the conside…