activity
20192022
most citedOn neural network kernels and the storage capacity problem

8 citations · 9 across the 2 of their papers we have counts for

collaborators

6 papers

cond-mat.dis-nn20228 cited

On neural network kernels and the storage capacity problem

Jacob A. Zavatone-Veth, Cengiz Pehlevan

In this short note, we reify the connection between work on the storage capacity problem in wide two-layer treelike neural networks and the rapidly-growing body of literature on ke…

cond-mat.dis-nn2020

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…

cs.LG2020

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…

cs.LG2020

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…

stat.ML20191 cited

A Closer Look at Disentangling in -VAE

Harshvardhan Sikka, Weishun Zhong, Jun Yin +1

In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating f…

q-bio.NC2019

Neuroscience-inspired online unsupervised learning algorithms

Cengiz Pehlevan, Dmitri B. Chklovskii

Although the currently popular deep learning networks achieve unprecedented performance on some tasks, the human brain still has a monopoly on general intelligence. Motivated by th…