Search Results for author: Robert M. Patton

Found 5 papers, 0 papers with code

An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment

no code implementations2 Sep 2021 James S. Plank, Catherine D. Schuman, Robert M. Patton

The OpenAI Gym project contains hundreds of control problems whose goal is to provide a testbed for reinforcement learning algorithms.

OpenAI Gym reinforcement-learning +1

Exascale Deep Learning to Accelerate Cancer Research

no code implementations26 Sep 2019 Robert M. Patton, J. Travis Johnston, Steven R. Young, Catherine D. Schuman, Thomas E. Potok, Derek C. Rose, Seung-Hwan Lim, Junghoon Chae, Le Hou, Shahira Abousamra, Dimitris Samaras, Joel Saltz

Using MENNDL--an HPC-enabled software stack for neural architecture search--we generate a neural network with comparable accuracy to state-of-the-art networks on a cancer pathology dataset that is also $16\times$ faster at inference.

Neural Architecture Search

Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study

no code implementations WS 2018 Drahomira Herrmannova, Steven R. Young, Robert M. Patton, Christopher G. Stahl, Nicole C. Kleinstreuer, Mary S. Wolfe

Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks.

A Survey of Neuromorphic Computing and Neural Networks in Hardware

no code implementations19 May 2017 Catherine D. Schuman, Thomas E. Potok, Robert M. Patton, J. Douglas Birdwell, Mark E. Dean, Garrett S. Rose, James S. Plank

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture.

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

no code implementations15 Mar 2017 Thomas E. Potok, Catherine Schuman, Steven R. Young, Robert M. Patton, Federico Spedalieri, Jeremy Liu, Ke-Thia Yao, Garrett Rose, Gangotree Chakma

Current Deep Learning approaches have been very successful using convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers.

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