Comparing continual task learning in minds and machines

TLDR

Humans learn multiple tasks over a lifetime, requiring interference‑free representations, a challenge mirrored in machine learning’s unsolved continual learning problem. The study examined error patterns in humans and advanced neural networks as they learned new tasks from scratch without instruction. We compared human and neural network error patterns during task acquisition from scratch without instruction. Humans benefit from blocked, task‑separated training when they possess a bias toward stimulus representations that promote task separation, whereas machines with a similar bias experience reduced interference, pointing to new strategies for artificial continual learning.

Abstract

Significance Humans learn to perform many different tasks over the lifespan, such as speaking both French and Spanish. The brain has to represent task information without mutual interference. In machine learning, this “continual learning” is a major unsolved challenge. Here, we studied the patterns of errors made by humans and state-of-the-art neural networks while they learned new tasks from scratch and without instruction. Humans, but not machines, seem to benefit from training regimes that blocked one task at a time, especially when they had a prior bias to represent stimuli in a way that encouraged task separation. Machines trained to exhibit the same prior bias suffered less interference between tasks, suggesting new avenues for solving continual learning in artificial systems.