PERCEPTRON-LIKE LEARNING IN TIME-SUMMATING NEURAL NETWORKS
PERCEPTRON-LIKE LEARNING IN TIME-SUMMATING NEURAL NETWORKS
复制标题
DOI：
10.1088/0305-4470/25/16/014
复制
发表时间：
1992-08-21
期刊：
影响因子：
--
通讯作者：
TAYLOR, JG
中科院分区：
文献类型：
--
作者：
BRESSLOFF, PC;TAYLOR, JG
本文研究了单层时间求和神经网络关联和存储时间序列的能力。特别是，时间序列的联想学习被重新表述为一个等效的分类任务，涉及静态模式。这导致了感知器的学习规则和收敛定理的时间序列的情况下的推广。使用基于线性可分性的几何参数，它显示了如何一个时间求和网络可以处理时间特性，如排序和协同发音效果。这样的能力是这样一个事实的结果，即时间求和网络开发了一个活动轨迹，该轨迹由网络之前所有输入的衰减总和组成。另一方面，在存在噪声输入的情况下，这样的活动轨迹也可能导致错误的累积。这促使修改的感知器的学习规则，包括引入一个稳定性参数，保证一定程度的鲁棒性噪声。网络的性能，在随机输入序列的存在下，然后分析使用螺旋机械技术。最后，它显示了如何，小的修改，时间求和网络可以训练存储和召回复杂的序列。
This paper investigates the ability of a single-layer, time-summating neural network to associate and store temporal sequences. In particular, the associative learning of temporal sequences is reformulated as an equivalent classification task involving static patterns. This leads to a generalization of the perceptron learning rule and convergence theorem to the case of temporal sequences. Using geometrical arguments based on linear separability it is shown how a time-summating network can handle temporal features such as ordering and coarticulation effects. Such an ability is a consequence of the fact that the time-summating network develops an activity trace consisting of a decaying sum of all previous inputs to the network. On the other hand, such an activity trace may also lead to an accumulation of errors in the presence of noisy inputs. This motivates a modification of the perceptron learning rule involving the introduction of a stability parameter that guarantees a certain level of robustness to noise. The performance of the network in the presence of random input sequences is then analysed using statistical-mechanical techniques. Finally, it is shown how, with small modifications, the time-summating network can be trained to store and recall complex sequences.