Quality of neural network mappings may be evaluated by visual inspection of hidden and output node activities for the training dataset. This paper discusses how to visualize such multidimensional data, introducing a new projection on a lattice of hypercube nodes. It also discusses what type of information one may expect from visualization of the activity of hidden and output layers. Detailed an...

Table 1: Phoneme recognition rates for diierent hybrid RBF-HMM systems; all values in %. In line two the results for a NN with one additional hidden layer of 100 sigmoidal units are depicted. The recognition rates for both training procedures are inferior to the net without hidden layer. This is mainly contributed to the relatively small hidden layer with 100 nodes, which acts like a bottleneck...

Artificial neural networks have been showed their effectiveness in many real world problems such as signal processing, pattern recognition, and classification problems. Although they provide highly generalized solutions, we find several unanswered problems in using artificial neural networks. Determining the most appropriate architecture of artificial neural network is identified as one of thos...

We propose an online learning algorithm for large margin training of continuous density hidden Markov models. The online algorithm updates the model parameters incrementally after the decoding of each training utterance. For large margin training, the algorithm attempts to separate the log-likelihoods of correct and incorrect transcriptions by an amount proportional to their Hamming distance. W...

The effect of post-training intradorsal striatal infusion of metabotropic glutamate receptor (mGluR) drugs on memory consolidation processes in an inhibitory avoidance (IA) task and visible/hidden platform water maze tasks was examined. In the IA task, adult male Long-Evans rats received post-training intracaudate infusions of the broad spectrum mGluR antagonist alpha-methyl-4-carboxyphenylglyc...

This paper presents the use of artificial neural network for the estimation of different performance parameters (i.e. Directivity, Radiation Efficiency, Gain and Bandwidth) of a coaxial feed equilateral triangular microstrip patch antenna. Levenberg-Marquardt training algorithms of MLPFFBP-ANN (Multilayer Perceptron feed forward back propagation Artificial Neural Network) has been used to imple...