Picture for Ryan Pyle

Ryan Pyle

A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks

Add code
Jul 14, 2023
Viaarxiv icon

Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics

Add code
Aug 04, 2020
Figure 1 for Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Figure 2 for Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Figure 3 for Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Figure 4 for Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Viaarxiv icon

Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples

Add code
Jun 19, 2020
Figure 1 for Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples
Figure 2 for Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples
Figure 3 for Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples
Figure 4 for Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples
Viaarxiv icon

A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways

Add code
Mar 08, 2018
Figure 1 for A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Figure 2 for A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Figure 3 for A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Figure 4 for A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Viaarxiv icon