Daucé Emmanuel, Quoy Mathias, Doyon Bernard
Movement and Perception (UMR6559), Faculty of Sport Science, University of the Mediterranean, 163, avenue de Luminy, CP 910, 13288 Marseille cedex 9, France.
Biol Cybern. 2002 Sep;87(3):185-98. doi: 10.1007/s00422-002-0315-4.
Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives stimulating spatiotemporal signals, and the secondary layer is a fully connected random recurrent network. This secondary layer spontaneously displays complex chaotic dynamics. All connections have a constant time delay. We use for our experiments a Hebbian (covariance) learning rule. This rule slowly modifies the weights under the influence of a periodic stimulus. The effect of learning is twofold: (i) it simplifies the secondary-layer dynamics, which eventually stabilizes to a periodic orbit; and (ii) it connects the secondary layer to the primary layer, and realizes a feedback from the secondary to the primary layer. This feedback signal is added to the incoming signal, and matches it (i.e., the secondary layer performs a one-step prediction of the forthcoming stimulus). After learning, a resonant behavior can be observed: the system resonates with familiar stimuli, which activates a feedback signal. In particular, this resonance allows the recognition and retrieval of partial signals, and dynamic maintenance of the memory of past stimuli. This resonance is highly sensitive to the temporal relationships and to the periodicity of the presented stimuli. When we present stimuli which do not match in time or space, the feedback remains silent. The number of different stimuli for which resonant behavior can be learned is analyzed. As with Hopfield networks, the capacity is proportional to the size of the second, recurrent layer. Moreover, the high capacity displayed allows the implementation of our model on real-time systems interacting with their environment. Such an implementation is reported in the case of a simple behavior-based recognition task on a mobile robot. Finally, we present some functional analogies with biological systems in terms of autonomy and dynamic binding, and present some hypotheses on the computational role of feedback connections.
通过与感知生物系统的结构进行全局类比，我们提出了一个由两层实值Sigmoid神经元组成的系统。初级层接收刺激的时空信号，次级层是一个全连接的随机递归网络。该次级层自发地表现出复杂的混沌动力学。所有连接都有恒定的时间延迟。我们在实验中使用赫布（协方差）学习规则。该规则在周期性刺激的影响下缓慢修改权重。学习的效果有两方面：（i）它简化了次级层的动力学，最终稳定到一个周期性轨道；（ii）它将次级层连接到初级层，并实现从次级层到初级层的反馈。这个反馈信号被添加到输入信号中，并与之匹配（即次级层对即将到来的刺激进行一步预测）。学习后，可以观察到一种共振行为：系统与熟悉的刺激产生共振，从而激活一个反馈信号。特别地，这种共振允许识别和检索部分信号，并动态维持对过去刺激的记忆。这种共振对所呈现刺激的时间关系和周期性高度敏感。当我们呈现时间或空间上不匹配的刺激时，反馈保持沉默。分析了可以学习到共振行为的不同刺激的数量。与霍普菲尔德网络一样，容量与第二个递归层的大小成正比。此外，所展示的高容量使得我们的模型能够在与环境交互的实时系统上实现。在移动机器人上基于简单行为的识别任务的情况下报告了这样一种实现。最后，我们在自主性和动态绑定方面提出了一些与生物系统的功能类比，并提出了一些关于反馈连接计算作用的假设。
