Brain-inspired Distributed Memorization Learning for Efficient Feature-free Unsupervised Domain Adaptation

arXiv:2402.14598v1 Announce Type: cross
Abstract: Compared with gradient based artificial neural networks, biological neural networks usually show a more powerful generalization ability to quickly adapt to unknown environments without using any gradient back-propagation procedure. Inspired by the distributed memory mechanism of human brains, we propose a novel gradient-free Distributed Memorization Learning mechanism, namely DML, to support quick domain adaptation of transferred models. In particular, DML adopts randomly connected neurons to memorize the association of input signals, which are propagated as …

abstract adapt artificial artificial neural networks arxiv brain brain-inspired brains cs.lg cs.ne distributed domain domain adaptation environments feature free gradient human memory networks neural networks novel propagation show type unsupervised