← Search

Joseph Shenouda

2 accepted papers

2024

A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning

NeurIPS 2024poster

This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual task resemble those obtained by solving a kernel regr…

Cited by 0SourcePDFScholar
2024

ReLUs Are Sufficient for Learning Implicit Neural Representations

ICML 2024poster

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations (INRs). Inspired by second order B-spline wavelets, we incorpo…