Steven Young

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).

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…

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

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…

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

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…

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…

Gordon Bell Chart

Our deep learning framework is called Multinode Evolutionary Neural Networks for Deep Learning (MENNDL).  MENNDL relies on two optimization methods, genetic algorithms and support vector…