180 citations · 449 across the 14 of their papers we have counts for
15 papers
Meta-Learning the Inductive Biases of Simple Neural Circuits
William Dorrell, Maria Yuffa, Peter Latham
Training data is always finite, making it unclear how to generalise to unseen situations. But, animals do generalise, wielding Occam's razor to select a parsimonious explanation of…
Actionable Neural Representations: Grid Cells from Minimal Constraints
William Dorrell, Peter E. Latham, Timothy E. J. Behrens +1
To afford flexible behaviour, the brain must build internal representations that mirror the structure of variables in the external world. For example, 2D space obeys rules: the sam…
Encoding priors in the brain: a reinforcement learning model for mouse decision making
Sanjukta Krishnagopal, Peter Latham
In two-alternative forced choice tasks, prior knowledge can improve performance, especially when operating near the psychophysical threshold. For instance, if subjects know that on…
Powerpropagation: A sparsity inducing weight reparameterisation
Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu +2
The training of sparse neural networks is becoming an increasingly important tool for reducing the computational footprint of models at training and evaluation, as well enabling th…
Towards Biologically Plausible Convolutional Networks
Roman Pogodin, Yash Mehta, Timothy P. Lillicrap +1
Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accurac…
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
Roman Pogodin, Peter E. Latham
The state-of-the art machine learning approach to training deep neural networks, backpropagation, is implausible for real neural networks: neurons need to know their outgoing weigh…