A more biologically plausible learning rule than backpropagation applied to a network model of cortical area 7a.
A more biologically plausible learning rule than backpropagation applied to a network model of cortical area 7a.
复制标题
比反向传播在生物学上更合理的学习规则应用于皮质区域 7a 的网络模型。
DOI：
10.1093/cercor/1.4.293
复制
发表时间：
1991
期刊：
影响因子：
--
通讯作者：
Jordan,MI
中科院分区：
文献类型：
--
作者：
Mazzoni,P;Andersen,RA;Jordan,MI
灵长类动物大脑后顶叶皮层的7a区通过结合视觉刺激的视网膜位置和眼睛在眼眶中的位置的信息来表示以头部为中心的空间。一个人工神经网络先前被训练来使用反向传播学习过程执行这个坐标转换任务，并且其中间层中的单元（隐藏单元）开发出与假定编码空间位置的7a区神经元非常相似的属性（Andersen和Zipser，1988; Zipser和Andersen，1988）。我们开发了两个神经网络，其架构类似于Zipser和Andersen的模型，并使用比反向传播更生物合理的学习过程来训练它们执行相同的任务。该过程是关联奖惩（AR-P）算法（Barto和Anandan，1985）的修改，其使用全局强化信号和局部突触信息来调整连接强度。我们的网络学习以任何程度的准确性成功地执行任务，并且几乎与反向传播一样快，隐藏单元开发出与la区神经元非常相似的响应特性。特别是，在我们的网络中，隐藏单元的发射概率随着眼睛位置的变化而变化，大致呈平面状，它们的视觉感受野很大，具有复杂的表面。用AR-P算法计算的突触强度与用反向传播算法计算的突触强度是等价的，可以互换。我们的网络还可以对以前从未遇到过的眼睛和视网膜位置进行正确的转换。所有这些发现都不受隐藏层和输出层之间插入额外单元层的影响。这些结果表明，经过训练以执行坐标变换的分层网络的隐藏单元的响应特性及其与7a区神经元的相似性，并不是反向传播训练的特定结果。它们可以通过生物学上更合理的学习规则获得的事实证实了该神经网络的计算算法作为区域7a可以如何执行坐标变换的合理模型的有效性。
Area 7a of the posterior parietal cortex of the primate brain is concerned with representing head-centered space by combining information about the retinal location of a visual stimulus and the position of the eyes in the orbits. An artificial neural network was previously trained to perform this coordinate transfonnation task using the backpropagation learning procedure, and units in its middle layer (the hidden units) developed properties very similar to those of area 7a neurons presumed to code for spatial location (Andersen and Zipser, 1988; Zipser and Andersen, 1988). We developed two neural networks with architecture similar to Zipser and Andersen's model and trained them to perform the same task using a more biologically plausible learning procedure than backpropagation. This procedure is a modification of the Associative Reward-Penalty (AR-P) algorithm (Barto and Anandan, 1985), which adjusts connection strengths using a global reinforcement signal and local synaptic information. Our networks learn to perform the task successfully to any degree of accuracy and almost as quickly as with backpropagation, and the hidden units develop response properties very similar to those of area la neurons. In particular, the probability of firing of the hidden units in our networks varies with eye position in a roughly planar fashion, and their visual receptive fields are large and have complex surfaces. The synaptic strengths computed by the AR-Palgorithm are equivalent to and interchangeable with those computed by backpropagation. Our networks also perform the correct transformation on pairs of eye and retinal positions never encountered before. All of these findings are unaffected by the interposition of an extra layer of units between the hidden and output layers. These resuits show that the response properties of the hidden units of a layered network trained to perform coordinate transfonnations, and their similarity with those of area 7a neurons, are not a specific result of backpropagation training. The fact that they can be obtained by a more biologically plausible learning rule corroborates the validity of this neural network's computational algorithm as a plausible model of how area 7a may perform coordinate transformations.