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.

Orthogonal representations for robust contextdependent task performance in brains and neural networks Highlights d We trained artificial neural networks and humans on contextdependent decision tasks d Initial weight variance determined the network's representational geometry d Human fronto-parietal representations were similar to those of low-variance networks d Theory of nonlinear gating explains how these are formed in neural networks and brains

How do neural populations code for multiple, potentially conflicting tasks? Here, we used computational simulations involving neural networks to define “lazy” and “rich” coding solutions to this multitasking problem, which trade off learning speed for robustness. During lazy learning the input dimensionality is expanded by random projections to the network hidden layer, whereas in rich learning hidden units acquire structured representations that privilege relevant over irrelevant features. For context-dependent decision-making, one rich solution is to project task representations onto low-dimensional and orthogonal manifolds. Using behavioural testing and neuroimaging in humans, and analysis of neural signals from macaque prefrontal cortex, we report evidence for neural coding patterns in biological brains whose dimensionality and neural geometry are consistent with the rich learning regime.

No abstract

Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, 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. We augment standard stochastic gradient descent with two algorithmic motifs, so-called “sluggish” task units and a Hebbian training step that strengthens connections between task units and hidden units that encode task-relevant information. We found that the “sluggish” units introduce a switch-cost during training, which biases representations under interleaved training towards a joint representation that ignores the contextual cue, while the Hebbian step promotes the formation of a gating scheme from task units to the hidden layer that produces orthogonal representations which are perfectly guarded against interference. Validating the model on previously published human behavioural data revealed that it matches performance of participants who had been trained on blocked or interleaved curricula, and that these performance differences were driven by misestimation of the true category boundary.