Pehlevan Group

Our research areas are theoretical neuroscience and theory of neural computation in natural and artificial systems.

Latest Publications and Preprints

J. A. Zavatone-Veth*, J. A. Rubinfien*, and C. Pehlevan, “Training shapes the curvature of shallow neural network representations,” in NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022.

M. Farrell*, B. Bordelon*, S. Trivedi, and C. Pehlevan, “Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?” in NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations (Oral), 2022.

B. Bordelon and C. Pehlevan, “Dynamical Mean Field Theory of Kernel Evolution in Wide Neural Networks,” in NeurIPS 2022 workshop on Machine Learning and the Physical Sciences, 2022.

J. A. Zavatone-Veth, W. Tong, and C. Pehlevan, “Contrasting random and learned features in deep Bayesian linear regression,” in NeurIPS 2022 workshop on Machine Learning and the Physical Sciences, 2022.

B. Bozkurt, A. Isfendiyaroglu, C. Pehlevan, and A. T. Erdogan, “Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation,” arXiv preprint arXiv:2210.04222, 2022.

A. Canatar and C. Pehlevan, “A Kernel Analysis of Feature Learning in Deep Neural Networks,” 2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton). 2022.

B. Bordelon and C. Pehlevan, “The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks,” arXiv preprint arXiv:2210.02157, 2022.

D. Lipshutz, C. Pehlevan, and D. B. Chklovskii, “Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation ,” arXiv preprint arXiv:2209.10634, 2022.

Copyright © 2022 The President and Fellows of Harvard College | Privacy | Accessibility | Digital Accessibility | Report Copyright Infringement