The cost of maintaining a given level of activity in a neuronal network depends on its size and degree of connectivity. Should a neural function require large-size fully-connected ...
—This paper describes a method of linearizing the nonlinear characteristics of many sensors using an embedded neural network. The proposed method allows for complex neural networ...
Abstract. Reservoir Computing (RC) uses a randomly created recurrent neural network where only a linear readout layer is trained. In this work, RC is used for detecting complex eve...
Eric A. Antonelo, Benjamin Schrauwen, Xavier Dutoi...
Abstract. We present a model of a recurrent neural network with homeostasic units, embodied in a minimalist articulated agent with a single link and joint. The configuration of th...
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...