no code implementations • 2 Jun 2023 • Samuel Schmidgall, Joe Hays
Legged robots operating in real-world environments must possess the ability to rapidly adapt to unexpected conditions, such as changing terrains and varying payloads.
no code implementations • 25 Jun 2022 • Samuel Schmidgall, Joe Hays
We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning.
no code implementations • 18 Nov 2021 • Cody Scharzenberger, Joe Hays
We aim to address this problem by training a neural network, which we will refer to as a "safety network", to estimate the region of attraction (ROA) of a controlled autonomous dynamical system.
no code implementations • 7 Nov 2021 • Samuel Schmidgall, Joe Hays
A recent resurgence of interest has developed in utilizing Artificial Neural Networks (ANNs) together with synaptic plasticity for intra-lifetime learning.
no code implementations • 4 Jun 2021 • Samuel Schmidgall, Julia Ashkanazy, Wallace Lawson, Joe Hays
The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks.