Search Results for author: William Severa

Found 10 papers, 0 papers with code

Stochastic Neuromorphic Circuits for Solving MAXCUT

no code implementations5 Oct 2022 Bradley H. Theilman, Yipu Wang, Ojas D. Parekh, William Severa, J. Darby Smith, James B. Aimone

By designing circuits and algorithms that make use of randomness similarly to natural brains, we hypothesize that the intrinsic randomness in microelectronics devices could be turned into a valuable component of a neuromorphic architecture enabling more efficient computations.

MIKE - Multi-task Implicit Knowledge Embeddings by Autoencoding through a Shared Input Space

no code implementations29 Sep 2021 Ryan Anthony Dellana, William Severa, Felix Wang, Esteban J Guillen, Jaimie Murdock

In this work, we introduce a method of learning Multi-task Implicit Knowledge Embeddings (MIKE) from a set of source (or "teacher") networks by autoencoding through a shared input space.

Neuromorphic scaling advantages for energy-efficient random walk computation

no code implementations27 Jul 2021 J. Darby Smith, Aaron J. Hill, Leah E. Reeder, Brian C. Franke, Richard B. Lehoucq, Ojas Parekh, William Severa, James B. Aimone

Computing stands to be radically improved by neuromorphic computing (NMC) approaches inspired by the brain's incredible efficiency and capabilities.

Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment

no code implementations21 Apr 2020 Maryam Parsa, Catherine D. Schuman, Prasanna Date, Derek C. Rose, Bill Kay, J. Parker Mitchell, Steven R. Young, Ryan Dellana, William Severa, Thomas E. Potok, Kaushik Roy

In this work, we introduce a Bayesian approach for optimizing the hyperparameters of an algorithm for training binary communication networks that can be deployed to neuromorphic hardware.

Hyperparameter Optimization

Evaluating complexity and resilience trade-offs in emerging memory inference machines

no code implementations25 Feb 2020 Christopher H. Bennett, Ryan Dellana, T. Patrick Xiao, Ben Feinberg, Sapan Agarwal, Suma Cardwell, Matthew J. Marinella, William Severa, Brad Aimone

Neuromorphic-style inference only works well if limited hardware resources are maximized properly, e. g. accuracy continues to scale with parameters and complexity in the face of potential disturbance.

Composing Neural Algorithms with Fugu

no code implementations28 May 2019 James B. Aimone, William Severa, Craig M. Vineyard

Rather than necessitating a developer attain intricate knowledge of how to program and exploit spiking neural dynamics to utilize the potential benefits of neuromorphic computing, Fugu is designed to provide a higher level abstraction as a hardware-independent mechanism for linking a variety of scalable spiking neural algorithms from a variety of sources.

Making BREAD: Biomimetic strategies for Artificial Intelligence Now and in the Future

no code implementations4 Dec 2018 Jeffrey L. Krichmar, William Severa, Salar M. Khan, James L. Olds

First, that scientific societies and governments coordinate Biomimetic Research for Energy-efficient, AI Designs (BREAD); a multinational initiative and a funding strategy for investments in the future integrated design of energetics into AI.

Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication

no code implementations26 Oct 2018 William Severa, Craig M. Vineyard, Ryan Dellana, Stephen J. Verzi, James B. Aimone

We present a method for training deep spiking neural networks using an iterative modification of the backpropagation optimization algorithm.

General Classification Image Classification +1

Spiking Neural Algorithms for Markov Process Random Walk

no code implementations1 May 2018 William Severa, Rich Lehoucq, Ojas Parekh, James B. Aimone

The random walk is a fundamental stochastic process that underlies many numerical tasks in scientific computing applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.