This article presents a language-independent emotion recognition system for the identification of human affective state in the speech signal. A group of potential features are first identified and extracted to represent the characteristics of different emotions. To reduce the dimensionality of the feature space, whilst increasing the discriminatory power of the features, we introduce a systemat...

We study the generalization capability of a modular neural network`the mixture of experts' that learn from examples generated by another network with the same architecture. When the number of examples is smaller than a critical value, the network shows a symmetric phase where the role of the experts is not specialized. Upon crossing the critical point, the system undergoes a continuous phase tr...

There is strong evidence that face processing in the brain is localized. The double dissociation between prosopagnosia, a face recognition de cit occurring after brain damage, and visual object agnosia, di culty recognizing other kinds of complex objects, indicates that face and non-face object recognition may be served by partially independent neural mechanisms. In this chapter, we use computa...

Since the conventional feedforward neural networks for character recognition have been designed to classify a large number of classes with one large network structure, inevitably it poses the very complex problem of determining the optimal decision boundaries for all the classes involved in a high-dimensional feature space. Limitations also exist in several aspects of the training and recogniti...

A sandwich-structured flexible supercapacitor electrode has been developed based on MnO2 nanonest (MNN) modified ionic liquid (IL) functionalized graphene paper (GP), which is fabricated by functionalizing graphene nanosheets with an amine-terminated IL (i.e., 1-(3-aminopropyl)-3-methylimidazolium bromide) to form freestanding IL functionalized GP (IL-GP), and then modifying IL-GP with a unique...