Back

Modular representations emerge in neural networks trained to perform context-dependent tasks

Johnston, W. J.; Fusi, S.

2024-10-11 neuroscience
10.1101/2024.09.30.615925 bioRxiv
Show abstract

Experimental and theoretical work has argued both for and against the existence of specialized sub-populations of neurons (modules) within single brain regions. By studying artificial neural networks, we show that this local modularity emerges to support complex (for instance, context-dependent) behavior only when the input to the network is low-dimensional. No anatomical constraints are required. We also show when modular specialization emerges implicitly at the population level, where orthogonal subspaces are viewed as distinct modules. Modularity yields abstract representations, allows for rapid learning and generalization on novel output domains as well as related tasks. Non-modular representations facilitate the rapid learning of unrelated tasks. Our findings reconcile conflicting experimental results and make predictions for future experiments.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.