106 citations · 317 across the 65 of their papers we have counts for
4 papers · 1 filter
Activation function dependence of the storage capacity of treelike neural networks
Jacob A. Zavatone-Veth, Cengiz Pehlevan
The expressive power of artificial neural networks crucially depends on the nonlinearity of their activation functions. Though a wide variety of nonlinear activation functions have…
Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks
Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan
Generalization beyond a training dataset is a main goal of machine learning, but theoretical understanding of generalization remains an open problem for many models. The need for a…
Contrastive Similarity Matching for Supervised Learning
Shanshan Qin, Nayantara Mudur, Cengiz Pehlevan
We propose a novel biologically-plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In bot…
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks
Blake Bordelon, Abdulkadir Canatar, Cengiz Pehlevan
We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian pro…