Learning to learn with backpropagation of Hebbian plasticity
This work addresses the problem of enabling lifelong learning in artificial neural networks for AI systems, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackled the challenge of integrating Hebbian plasticity into artificial neural networks by deriving analytical expressions for activity gradients, enabling backpropagation to train both baseline weights and plasticity, resulting in networks that automatically perform fast learning of unpredictable features during their lifetime. It demonstrated success on tasks like pattern completion and one-shot learning, allowing for continual learning in changing environments.
Hebbian plasticity is a powerful principle that allows biological brains to learn from their lifetime experience. By contrast, artificial neural networks trained with backpropagation generally have fixed connection weights that do not change once training is complete. While recent methods can endow neural networks with long-term memories, Hebbian plasticity is currently not amenable to gradient descent. Here we derive analytical expressions for activity gradients in neural networks with Hebbian plastic connections. Using these expressions, we can use backpropagation to train not just the baseline weights of the connections, but also their plasticity. As a result, the networks "learn how to learn" in order to solve the problem at hand: the trained networks automatically perform fast learning of unpredictable environmental features during their lifetime, expanding the range of solvable problems. We test the algorithm on various on-line learning tasks, including pattern completion, one-shot learning, and reversal learning. The algorithm successfully learns how to learn the relevant associations from one-shot instruction, and fine-tunes the temporal dynamics of plasticity to allow for continual learning in response to changing environmental parameters. We conclude that backpropagation of Hebbian plasticity offers a powerful model for lifelong learning.