Galtier Mathieu
Minds, Jacobs University Bremen, Bremen, Germany,
Biol Cybern. 2015 Jun;109(3):363-75. doi: 10.1007/s00422-015-0648-4. Epub 2015 Mar 10.
The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show a promising performance of the approach, which can be turned into a local and better "biologically plausible" algorithm.
本文介绍了一种用于控制未知环境的神经网络架构。它基于一个随机连接的递归神经网络，在该网络中，感知和动作同时被读取并反馈。有两种并行的学习规则实现了一种意向运动控制：（i）感知学习遵循网络应可靠预测其传入刺激的原则；（ii）动作学习遵循网络的预测应与目标时间序列匹配的原则。神经网络在其环境中的连贯行为是这两种原则相互作用的结果。数值模拟显示了该方法具有良好的性能，可将其转化为一种局部且更具 “生物学合理性” 的算法。
