Multi-context blind source separation by error-gated Hebbian rule
Animals need to adjust their inferences according to the context they are in. This is required for the multi-context blind source separation (BSS) task, where an agent needs to infer hidden sources from their context-dependent mixtures. The agent is expected to invert this mixing process for all contexts. Here, we show that a neural network that implements the error-gated Hebbian rule (EGHR) with sufficiently redundant sensory inputs can successfully learn this task. After training, the network can perform the multi-context BSS without further updating synapses, by retaining memories of all experienced contexts. Finally, if there is a common feature shared across contexts, the EGHR can extract it and generalize the task to even inexperienced contexts. This demonstrates an attractive use of the EGHR for dimensionality reduction by extracting common sources across contexts. The results highlight the utility of the EGHR as a model for perceptual adaptation in animals.