SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07617 · 2021

Algorithmic insights on continual learning from fruit flies

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2107.07617")
get_code_for_paper("2107.07617")
have("2107.07617")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2107.07617.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2107.07617.svg)](https://syntology.ai/paper/2107.07617)

Connect an agent — have() is free.