activity
20182022
most citedFine-Grained System Identification of Nonlinear Neural Circuits

3 citations · 4 across the 3 of their papers we have counts for

collaborators

8 papers

cs.NE2022

Optimisation & Generalisation in Networks of Neurons

Jeremy Bernstein

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framew…

q-bio.QM20213 cited

Fine-Grained System Identification of Nonlinear Neural Circuits

Dawna Bagherian, James Gornet, Jeremy Bernstein +3

We study the problem of sparse nonlinear model recovery of high dimensional compositional functions. Our study is motivated by emerging opportunities in neuroscience to recover fin…

cs.LG20211 cited

Computing the Information Content of Trained Neural Networks

Jeremy Bernstein, Yisong Yue

How much information does a learning algorithm extract from the training data and store in a neural network's weights? Too much, and the network would overfit to the training data.…

cs.NE2021

Learning by Turning: Neural Architecture Aware Optimisation

Yang Liu, Jeremy Bernstein, Markus Meister +1

Descent methods for deep networks are notoriously capricious: they require careful tuning of step size, momentum and weight decay, and which method will work best on a new benchmar…

cs.NE2020

Learning compositional functions via multiplicative weight updates

Jeremy Bernstein, Jiawei Zhao, Markus Meister +3

Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems l…

cs.LG2020

On the distance between two neural networks and the stability of learning

Jeremy Bernstein, Arash Vahdat, Yisong Yue +1

This paper relates parameter distance to gradient breakdown for a broad class of nonlinear compositional functions. The analysis leads to a new distance function called deep relati…