Title :
Spatio–Temporal Adaptation in the Unsupervised Development of Networked Visual Neurons
Author :
Chen, Dongyue ; Zhang, Liming ; Weng, Juyang John
Author_Institution :
Dept. of Electron. Eng., Fudan Univ., Shanghai
fDate :
6/1/2009 12:00:00 AM
Abstract :
There have been many computational models mimicking the visual cortex that are based on spatial adaptations of unsupervised neural networks. In this paper, we present a new model called neuronal cluster which includes spatial as well as temporal weights in its unified adaptation scheme. The ldquoin-placerdquo nature of the model is based on two biologically plausible learning rules, Hebbian rule and lateral inhibition. We present the mathematical demonstration that the temporal weights are derived from the delay in lateral inhibition. By training with the natural videos, this model can develop spatio-temporal features such as orientation selective cells, motion sensitive cells, and spatio-temporal complex cells. The unified nature of the adaption scheme allows us to construct a multilayered and task-independent attention selection network which uses the same learning rule for edge, motion, and color detection, and we can use this network to engage in attention selection in both static and dynamic scenes.
Keywords :
learning (artificial intelligence); neural nets; visual perception; Hebbian rule; biologically plausible learning rules; computational models; lateral inhibition; mathematical demonstration; multilayered attention selection network; networked visual neurons; neuronal cluster; spatio-temporal adaptation; task-independent attention selection network; unsupervised development; unsupervised neural networks; visual cortex; Attention selection; Hebbian learning rule; developmental algorithm; lateral inhibition; receptive fields (RFs); Algorithms; Biomimetics; Computer Simulation; Models, Theoretical; Nerve Net; Neural Networks (Computer); Pattern Recognition, Automated; Visual Perception;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2009.2015082