Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/17710
Title: Hardware radial basis functions neural networks for phoneme recognition
Authors: Gatt, Edward
Micallef, Joseph
Chilton, Edward
Keywords: Radial basis functions
Neural networks (Computer science)
Back propagation (Artificial intelligence)
Integrated circuits -- Very large scale integration
Issue Date: 2001
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Gatt, E., Micallef, J., & Chilton, E. (2001). Hardware radial basis functions neural networks for phoneme recognition. 8th IEEE International Conference on Electronics, Circuits and Systems, Malta. 627-630.
Abstract: The ability of a neural network to learn on-line is crucial for real time speech recognition systems. In fact, analog neural network systems are preferred to their digital counterparts mainly due to the high speed that they can attain. However, the training method adopted also affects the performance of the neural network. The conventional error backpropagation network usually requires quite a long convergence time for correct weight adjustment since the sigmoid function of a conventional multilayer network gives a smooth response over a wide range of input values. In contrast, the Gaussian function responds significantly only to local regions of the space of input values. Thus, backpropagation training is more efficient in neural networks based on Gaussian functions or radial basis function (RBF) networks, than those based on sigmoid functions in the hidden layer. The paper proposes an analog VLSI chip, which can be cascaded in order to develop an RBF neural network system for phoneme recognition.
URI: https://www.um.edu.mt/library/oar//handle/123456789/17710
Appears in Collections:Scholarly Works - FacICTMN

Files in This Item:
File Description SizeFormat 
Hardware Radial Basis Functions Neural Networks for Phoneme Recognition.pdf
  Restricted Access
Hardware radial basis functions neural networks for phoneme recognition333.99 kBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.