SignificanceHumans 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.

Generalization (or transfer) is the ability to repurpose knowledge in novel settings. It is often asserted that generalization is an important ingredient of human intelligence, but its extent, nature, and determinants have proved controversial. Here, we examine this ability with a paradigm that formalizes the transfer learning problem as one of recomposing existing functions to solve unseen problems. We find that people can generalize compositionally in ways that are elusive for standard neural networks and that human generalization benefits from training regimes in which items are axis aligned and temporally correlated. We describe a neural network model based around a Hebbian gating process that can capture how human generalization benefits from different training curricula. We additionally find that adult humans tend to learn composable functions asynchronously, exhibiting discontinuities in learning that resemble those seen in child development.

Humans can learn to perform multiple tasks in succession over the lifespan ("continual" learning), whereas current machine learning systems fail. Here, we investigated the cognitive mechanisms that permit successful continual learning in humans. Unlike neural networks, humans that were trained on temporally autocorrelated task objectives (focussed training) learned to perform new tasks more effectively, and performed better on a later test involving randomly interleaved tasks. Analysis of error patterns suggested that focussed learning permitted the formation of factorised task representations that were protected from mutual interference. Furthermore, individuals with a strong prior tendency to represent the task space in a factorised manner enjoyed greater benefit of focussed over interleaved training. Building artificial agents that learn to factorise tasks appropriately may be a promising route to solving continual task performance in machine learning.

Generalisation (or transfer) is the ability to repurpose knowledge in novel settings. It is often asserted that generalisation is an important ingredient of human intelligence, but its extent, nature and determinants have proved controversial. Here, we re-examine this question with a new paradigm that formalises the transfer learning problem as one of recomposing existing functions to solve unseen problems. We find that people can generalise compositionally in ways that are elusive for standard neural networks, and that human generalisation benefits from training regimes in which items are axis-aligned and temporally correlated. We describe a neural network model based around a Hebbian gating process which can capture how human generalisation benefits from different training curricula. We additionally find that adult humans tend to learn composable functions asynchronously, exhibiting discontinuities in learning that resemble those seen in child development.