Retrieval

One can now ask the question under which conditions recognition takes place? The computational interest of a recognition process relies on the ability to determine the frontier between acception or rejection of the incoming signal, and then to explicit (or interpret) the accepted signals, i.e. to determine "what" is recognized. On Fig.5, we use the same network as in the previous example. We then present two different input signals. Both of them are composed with the same elementary single input, corresponding to the stimulation of the first primary neuron, but the time delay between those individual stimulations are different: the delay is 3 in the first case, like in the learned sequence, and 4 in the second case, which implies a temporal misfit with the learned sequence. After a transient time, the system manages to fill the signal with the period-3 input. At time $t=65$, a change in the input periodicity takes place, which leads to a progressive decrease of the feedback signal.

Figure: Feedback retrieval of input pattern, after learning the elementary sequence $\mathbf{s}=(1,2,3)$. Input change is perceptible at $t=64$ (Change on input periodicity). $N^{(1)}=200$, $N^{(2)}=200$, other parameters are in Tab.1. - a - Neuronal activity on secondary layer. 20 individual signals are represented, with their mean activity. - b - Input signal (I) and Feedback reinforcement(F). Only the values corresponding to the three first primary neurons are represented between $t=11$ and $t=95$ (some time steps have been discarded for readability).

So, after learning, presenting a stimulus that has both spatial common points and a time coherency with the learned one leads the system towards a similar dynamical response, i.e towards a similar attractor and a similar feedback signal (this similarity can be measured in terms of spatio-temporal correlation between samples of the compared patterns of activation). The system can thus retrieve the missing information according to a partial signal (this retrieval ability also holds with spatially distributed inputs corrupted with a significant noise [8]. The robustness to natural noise is tested in section 5, in the case of a robotic application). Otherwise, the sensitivity to the period-3/period-4 change illustrates the major influence of the inner signal on the response of the system. As the inner dynamics is strongly period-sensitive, every change in the input period modifies the inner dynamical organization, and thus modifies the nature of the response.