54 citations · 94 across the 7 of their papers we have counts for
7 papers
The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity
Justin Sahs, Ryan Pyle, Fabio Anselmi +1
Despite classical statistical theory predicting severe overfitting, modern massively overparameterized neural networks still generalize well. This unexpected property is attributed…
A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
Ryan Pyle, Sebastian Musslick, Jonathan D. Cohen +1
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task. Different types of repr…
Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Justin Sahs, Ryan Pyle, Aneel Damaraju +4
Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented. W…
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples
Josue Ortega Caro, Yilong Ju, Ryan Pyle +4
Adversarial Attacks are still a significant challenge for neural networks. Recent work has shown that adversarial perturbations typically contain high-frequency features, but the r…
A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Ryan Pyle, Robert Rosenbaum
Many recent studies of the motor system are divided into two distinct approaches: Those that investigate how motor responses are encoded in cortical neurons' firing rate dynamics a…
Spatiotemporal dynamics and reliable computations in recurrent spiking neural networks
Ryan Pyle, Robert Rosenbaum
Randomly connected networks of excitatory and inhibitory spiking neurons provide a parsimonious model of neural variability, but are notoriously unreliable for performing computati…
Highly connected neurons spike less frequently in balanced networks
Ryan Pyle, Robert Rosenbaum
Many biological neuronal networks exhibit highly variable spiking activity. Balanced networks offer a parsimonious model of this variability. In balanced networks, strong excitator…