CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data

arXiv:2403.15974v1 Announce Type: cross
Abstract: This paper describes CBGT-Net, a neural network model inspired by the cortico-basal ganglia-thalamic (CBGT) circuits found in mammalian brains. Unlike traditional neural network models, which either generate an output for each provided input, or an output after a fixed sequence of inputs, the CBGT-Net learns to produce an output after a sufficient criteria for evidence is achieved from a stream of observed data. For each observation, the CBGT-Net generates a vector that explicitly represents the …

abstract architecture arxiv brains circuits classification cs.ai cs.cv cs.lg cs.ne data found generate inputs network neural network paper robust streaming streaming data type