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