Search Results for author:
Found 5 papers, 0 papers with code
A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
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.
Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Our implicit regularization results are complementary to recent work arXiv:1906. 07842, done independently, which showed that initialization scale critically controls implicit regularization via a kernel-based argument.
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples
Inspired by theoretical work on linear full-width convolutional models, we hypothesize that the local (i. e. bounded-width) convolutional operations commonly used in current neural networks are implicitly biased to learn high frequency features, and that this is one of the root causes of high frequency adversarial examples.
A Functional Characterization of Randomly Initialized Gradient Descent in Deep ReLU Networks
Despite their popularity and successes, deep neural networks are poorly understood theoretically and treated as 'black box' systems.
A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
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 and those that study the learning rules by which mammals and songbirds develop reliable motor responses.
