• Publications
  • Influence
Comparing continual task learning in minds and machines
Analysis of human error patterns suggested that blocked training encouraged humans to form “factorized” representation that optimally segregated the tasks, especially for those individuals with a strong prior bias to represent the stimulus space in a well-structured way.
Rich and lazy learning of task representations in brains and neural networks
Evidence is reported for neural coding patterns in biological brains whose dimensionality and neural geometry are consistent with the rich learning regime, using behavioural testing and neuroimaging in humans and analysis of neural signals from macaque prefrontal cortex.
Focused learning promotes continual task performance in humans
Analysis of error patterns suggested that focussed learning permitted the formation of factorised task representations that were protected from mutual interference, suggesting new avenues for solving continual learning in artificial systems.
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Novel computational constraints for artificial neural networks are proposed, inspired by earlier work on gating in the primate prefrontal cortex, that capture the cost of interleaved training and allow the network to learn two tasks in sequence without forgetting.
Complementary Brain Signals for Categorical Decisions
Apples come in various shapes, colors, and sizes, but humans can nonetheless easily distinguish them from other fruit (e.g., peaches) or other round objects (e.g., tennis balls). This capacity to