Medler D A, Dawson M R
Department of Psychology, University of Alberta, Edmonton, Canada.
Psychol Res. 1994;57(1):54-62. doi: 10.1007/BF00452996.
One biological principle that is often overlooked in the design of artificial neural networks (ANNs) is redundancy. Redundancy is the replication of processes within the brain. This paper examines the effects of redundancy on learning in ANNs when given either a function-approximation task or a pattern-classification task. The function-approximation task simulated a robotic arm reaching toward an object in two-dimensional space, and the pattern-classification task was detecting parity. Results indicated that redundant ANNs learned the pattern-classification problem much faster, and converge on a solution 100% of the time, whereas standard ANNs sometimes failed to learn the problem. Furthermore, when overall network error is considered, redundant ANNs were significantly more accurate than standard ANNs in performing the function-approximation task. These results are discussed in terms of the relevance of redundancy to the performance of ANNs in general, and the relevance of redundancy in biological systems in particular.
在人工神经网络（ANN）设计中常常被忽视的一个生物学原理是冗余性。冗余性是指大脑中过程的复制。本文研究了在给定函数逼近任务或模式分类任务时，冗余性对人工神经网络学习的影响。函数逼近任务模拟了一个机器人手臂在二维空间中伸向一个物体，模式分类任务是检测奇偶性。结果表明，冗余人工神经网络学习模式分类问题的速度要快得多，并且100%的情况下都能收敛到一个解决方案，而标准人工神经网络有时无法学会该问题。此外，当考虑整体网络误差时，冗余人工神经网络在执行函数逼近任务时比标准人工神经网络明显更准确。本文从冗余性与一般人工神经网络性能的相关性，特别是与生物系统中冗余性的相关性方面对这些结果进行了讨论。
