A contrastive rule for meta-learning
This work addresses the challenge of meta-learning in neural circuits, offering a biologically plausible method that could impact neuroscience and AI, though it appears incremental as it builds on contrastive Hebbian learning.
The authors tackled the problem of understanding how learning processes improve through experience by proposing a biologically-plausible meta-learning rule that estimates gradients without second derivatives or backpropagation in time. They demonstrated that this rule matches or outperforms reference algorithms on benchmark problems, using only locally available information.
Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically thought to underlie learning in the brain, the precise neural and synaptic mechanisms by which learning processes improve through experience are not well understood. Here, we present a general-purpose, biologically-plausible meta-learning rule which estimates gradients with respect to the parameters of an underlying learning algorithm by simply running it twice. Our rule may be understood as a generalization of contrastive Hebbian learning to meta-learning and notably, it neither requires computing second derivatives nor going backwards in time, two characteristic features of previous gradient-based methods that are hard to conceive in physical neural circuits. We demonstrate the generality of our rule by applying it to two distinct models: a complex synapse with internal states which consolidate task-shared information, and a dual-system architecture in which a primary network is rapidly modulated by another one to learn the specifics of each task. For both models, our meta-learning rule matches or outperforms reference algorithms on a wide range of benchmark problems, while only using information presumed to be locally available at neurons and synapses. We corroborate these findings with a theoretical analysis of the gradient estimation error incurred by our rule.