使用清醒-睡眠算法的MT和MST区域模型。

Models of MT and MST areas using wake-sleep algorithm.

作者信息

Katayama Katsuki, Ando Masataka, Horiguchi Tsuyoshi

机构信息

Research Institute of Electrical Communication, Tohoku University, Sendai 980-8577, Japan.

出版信息

Neural Netw. 2004 Apr;17(3):339-51. doi: 10.1016/j.neunet.2003.07.004.

DOI:10.1016/j.neunet.2003.07.004

PMID:15037352

Abstract

We present two-layered neural network models with Q (> or =2)-states neurons for a system with middle temporal (MT) neurons and medial superior temporal (MST) neurons by using a wake-sleep algorithm proposed by Hinton et al.; we notice that the wake-sleep algorithm consists of local learning rules. We first investigate a model with binary neurons for response properties of the MST neurons to optical flows as for various types of motion. We next extend the model with binary neurons to a model with Q (> or =3)-states neurons and investigate the response properties of the MST neurons for various values of Q (> or =3). We obtain better response properties for the model with Q (> or =3)-states neurons than for the one with binary neurons.

摘要

我们使用Hinton等人提出的醒-睡算法，针对具有中颞叶（MT）神经元和内侧颞上叶（MST）神经元的系统，提出了具有Q（≥2）状态神经元的两层神经网络模型；我们注意到醒-睡算法由局部学习规则组成。我们首先研究了一个具有二元神经元的模型，用于探究MST神经元对各种类型运动的光流的响应特性。接下来，我们将具有二元神经元的模型扩展为具有Q（≥3）状态神经元的模型，并研究了Q（≥3）的各种值下MST神经元的响应特性。我们发现，具有Q（≥3）状态神经元的模型比具有二元神经元的模型具有更好的响应特性。