In back-propagation (Rumelhart et al, 1985) connection weights are used to both compute node activations and error gradients for hidden units. Grossberg (1987) has argued that the dual use of the same synaptic connections (“weight transport”) constitutes a bidirectional flow of information through synapses, which is biologically implausable. In this paper we formally and empirically demonstrate...

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a nonlinear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back...

The disadvantages of the fuzzy BP learning are its low speed of error convergence and the high possibility of trapping into local minima. In this paper, a fuzzy proportional factor is added to the fuzzy BP’s iteration scheme to enhance the convergence speed. The added factor makes the proposed method more dependant on the distance of actual outputs and desired ones. Thus in contrast with the co...

Recent work has shown that in some cases the phase information of synaptic signal is important in the learning and representation capabilities of networks. Modelling such information with complex valued activation signals is possible, and indeed complex back-propagation algorithms have been derived 3]. Cliiord algebras give a way to generalise complex numbers to many dimensions. This paper pres...

breathomics is the metabolomics study of exhaled air. it is a powerful emerging metabolomics research field that mainly focuses onhealth-related volatile organic compounds (vocs). since the quantity of these compounds varies with health status, breathomics assuresto deliver noninvasive diagnostic tools. thus, the main aim of breathomics is to discover patterns of vocs related to abnormal metabo...

The supervised learning of the discriminative convolutional neural network (ConvNet or CNN) is powered by back-propagation on the parameters. In this paper, we show that the unsupervised learning of a popular top-down generative ConvNet model with latent continuous factors can be accomplished by a learning algorithm that consists of alternatively performing back-propagation on both the latent f...

A back-propagation neural network is applied to a nonlinear self-tuning tracking problem. Traditional self-tuning adaptive control techniques can only deal with linear systems or some special nonlinear systems. The emerging back-propagation neural networks have the capability to learn arbitrary nonlinearity and show great potential for adaptive control applications. A scheme for combining back-...