Catherine Schuman

Highlights

Coefficient of variation (CoV) and total fuel injected results for the best spiking neural networks for each generation of evolution for all ten runs for the engine simulator. The best network is defined as the network with the lowest fuel injected that is also below the CoV threshold of 3 percent (averaged over ten test runs).
Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

Neuromorphic computing offers one path forward for AI at the edge.  However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial.  In this work, researchers…

spiking neural network generated by EONS using the Caspian platform CDA ORNL
Caspian: A Neuromorphic Development Platform

Caspian provides a development platform for neuromorphic algorithms and applications research.  The C++ and Python APIs allow for quick and flexible development of new algorithms and…

Visual Analytics System Overview: The system consists of three different views: a lineage view (1), a fitness-parameter view (2), and a network architecture view (3). CDA ORNL
Visualization System for Evolutionary Neural Networks for Deep Learning

Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network…

Neuromorphic Graph Algorithms: Extracting Longest Shortest Paths and Minimum Spanning Trees

Neuromorphic architectures provide a low energy and highly parallelized framework for many tasks. In this document we demonstrate that neuromorphic computing systems can be used to deploy classical…

Summary of Bayesian-based Hyperparameter Optimization Results: a. Grid search: Whetstone accuracy for 256 different HP sets. b. Bayesian-based HP optimization: selected 15 HP combinations to find optimal hyperparameter set (shown with red star). c. Bayesian-based HP optimization result for four state-of-the-art datasets
Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment

In this work, the researchers introduced a Bayesian approach for optimizing the hyperparameters of an algorithm for training binary communication networks that can be deployed to neuromorphic…

EONS algorithm overview ORNL CDA Computer Data Analytics
Evolutionary Optimization for Neuromorphic Systems

Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, researchers from ORNL introduced an approach for…

Resilience and Robustness of Spiking Neural Networks for Neuromorphic Systems - CDA ORNL
Resilience and Robustness of Spiking Neural Networks for Neuromorphic Systems

Though robustness and resilience are commonly quoted as features of neuromorphic computing systems, the expected performance of neuromorphic systems in the face of hardware failures is not clear.…

Left - Memristive neuromorphic system Right - Spiking neural network designed by EONS
Automated Design of Neuromorphic Networks for Scientific Applications at the Edge

Designing spiking neural networks for neuromorphic deployment is a non-trivial task.  It is further complicated when there are resource constraints for the neuromorphic implementation, such as…

Bayesian-based Hyperparameter Optimization for Spiking Neuromorphic Systems
Bayesian-based Hyperparameter Optimization for Spiking Neuromorphic Systems

Designing a neuromorphic computing system involves selection of several hyperparameters that not only affect the accuracy of the framework, but also the energy efficiency and speed of inference and…

Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks

Neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the…

Evolving Energy Efficient Convolutional Neural Networks
Evolving Energy Efficient Convolutional Neural Networks

In this work, we discuss an approach for that utilizes high-performance computing (HPC) to evolve the hyperparameters and topology of convolutional neural networks in order to investigate the ability…