1 code implementation • 8 Nov 2023 • Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities.
no code implementations • 9 Aug 2023 • Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments.
no code implementations • 28 Mar 2023 • Matt Gorbett, Darrell Whitley
In addition to Iterative Weight Recycling, we complement the Multi-Prize Lottery Ticket Hypothesis with a reciprocal finding: high-accuracy, randomly initialized subnetwork's produce diverse masks, despite being generated with the same hyperparameter's and pruning strategy.
no code implementations • 28 Feb 2020 • Matt Gorbett, Nathaniel Blanchard
Neural networks are vulnerable to a wide range of erroneous inputs such as adversarial, corrupted, out-of-distribution, and misclassified examples.