Beren Millidge

This paper demonstrates that spontaneous adaptive organisation can arise from the interaction of physical optimisation and learning in dynamical systems, without natural selection.

This paper introduces a temporal predictive coding model implemented in recurrent networks that can predict future stimuli and produce neuron-like responses without complex computations.

This paper introduces a new credit assignment mechanism called prospective configuration, showing it can enable efficient learning in biological contexts and replicate observed neural behaviors.

The paper proposes a temporal difference model that explains how dopamine neurons encode different reward dimensions and adapts behavior based on physiological needs.

This paper proposes predictive coding models that implicitly learn covariance information for associative memory, unifying predictive coding and covariance learning in hippocampal networks.

The paper introduces an extension to temporal difference learning that enables instantaneous adaptation to changing reward functions without retraining.