Unknown

Dataset Information

0

Multi-context blind source separation by error-gated Hebbian rule.


ABSTRACT: 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. This demonstrates an attractive use of the EGHR for dimensionality reduction by extracting low-dimensional sources across contexts. Finally, if there is a common feature shared across contexts, the EGHR can extract it and generalize the task to even inexperienced contexts. The results highlight the utility of the EGHR as a model for perceptual adaptation in animals.

SUBMITTER: Isomura T 

PROVIDER: S-EPMC6509167 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

altmetric image

Publications

Multi-context blind source separation by error-gated Hebbian rule.

Isomura Takuya T   Toyoizumi Taro T  

Scientific reports 20190509 1


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  ...[more]

Similar Datasets

| S-EPMC5789861 | biostudies-other
| S-EPMC5994057 | biostudies-literature
| S-EPMC9543588 | biostudies-literature
| S-EPMC8747210 | biostudies-literature
| S-EPMC3188549 | biostudies-literature
| S-EPMC2525701 | biostudies-literature
| S-EPMC2711419 | biostudies-literature
| S-EPMC4493666 | biostudies-literature
| S-EPMC4686348 | biostudies-literature
| S-EPMC9971366 | biostudies-literature