Algorithmic insights on continual learning from fruit flies
This addresses the problem of catastrophic forgetting for machine learning systems, offering a biologically-inspired algorithm that is efficient and lightweight, though it is incremental as it builds on existing perceptron methods.
The paper tackled catastrophic forgetting in continual learning by discovering a two-layer neural circuit in fruit flies that combines sparse coding and associative learning, showing it significantly boosts performance with empirical and analytical evidence.
Continual learning in computational systems is challenging due to catastrophic forgetting. We discovered a two layer neural circuit in the fruit fly olfactory system that addresses this challenge by uniquely combining sparse coding and associative learning. In the first layer, odors are encoded using sparse, high dimensional representations, which reduces memory interference by activating non overlapping populations of neurons for different odors. In the second layer, only the synapses between odor activated neurons and the output neuron associated with the odor are modified during learning; the rest of the weights are frozen to prevent unrelated memories from being overwritten. We show empirically and analytically that this simple and lightweight algorithm significantly boosts continual learning performance. The fly associative learning algorithm is strikingly similar to the classic perceptron learning algorithm, albeit two modifications, which we show are critical for reducing catastrophic forgetting. Overall, fruit flies evolved an efficient lifelong learning algorithm, and circuit mechanisms from neuroscience can be translated to improve machine computation.