A Self-Organized Neural Comparator

A Self-Organized Neural Comparator

Learning algorithms need generally the ability to compare several streams of information. Neural learning architectures hence need a unit, a comparator, able to compare several inputs encoding either internal or external information, for instance, predictions and sensory readings. Without the possibility of comparing the values of predictions to actual sensory inputs, reward evaluation and supe...

Self-organized critical neural networks.

A mechanism for self-organization of the degree of connectivity in model neural networks is studied. Network connectivity is regulated locally on the basis of an order parameter of the global dynamics, which is estimated from an observable at the single synapse level. This principle is studied in a two-dimensional neural network with randomly wired asymmetric weights. In this class of networks,...

Reservoir Computing and Self-Organized Neural Hierarchies

There is a growing understanding that machine learning architectures have to be much bigger and more complex to approach any intelligent behavior. There is also a growing understanding that purely supervised learning is inadequate to train such systems. A recent paradigm of artificial recurrent neural network (RNN) training under the umbrella-name Reservoir Computing (RC) demonstrated that trai...

Self-organized criticality in adaptive neural networks

Self-organized criticality in neural network models

Information processing by a network of dynamical elements is a delicate matter: Avalanches of activity can die out if the network is not connected enough or if the elements are not sensitive enough; on the other hand, activity avalanches can grow and spread over the entire network and override information processing as observed in epilepsy. Therefore, it has long been argued that neural network...