This study proposes fuzzy matrix quantization (FMQ) which is a new coding technique developed to obtain discrete symbols employed for hidden Markov models (HMM's). FMQ is a coding technique combining fuzzy vector quantization with matrix quantization. The validity of FMQ is evaluated by a speaker-independent isolated word recognition task. First, the effect of FMQ is examined when FMQ is applied to the training phase and/or recognition phase. The effects of number of training data, codebook size and codeword matrix size for recognition accuracy are investigated. And the results of the speech recognition based on HMM recognizer using FMQ technique is compared with HMM recognizers using conventional quantization methods, vector quantization and fuzzy vector quantization. As a result, FMQ is the effective coding technique for isolated word recognition on condition that codebook size is large, above all, when FMQ is applied to the training phase and training data set is small.

In this research report a new VLSI block placement algorithm based on the Fuzzy theory is presented. The algorithm has such a feature that many factors related to the cost and performance of VLSI chips can be simultaneously considered. First, we explain the rules used to estimate the routes of wires. Using these rules the chip size containing the wiring space can be estimated. Then, three membership functions corresponding to the wire length and chip size are defined on the basis of the Fuzzy theory. Next, the Fuzzy inference space is introduced in order to determine the position of the VLSI blocks by using the membership functions, and a block placement algorithm using the Fuzzy inference is proposed. In the algorithm, the set of blocks is partitioned into subsets called piled blocks, the blocks in each subset are piled up from the bottom of the chip, and the piled blocks are arranged from the left side to the right side of the chip. In this placement process, Fuzzy inference is used as a criteria corresponding to the wire length and chip area to choose a candidate of block to be located. Experimental results are shown, and they are far superior to those obtained by other methods published in the literature so far.

A new timing driven placement method based on the fuzzy theory is proposed. In this method, the longest path delay, the chip area and the wire length can be simultaneously minimized. Introducing the probability measures of fuzzy events, falling down into the optimal solutions can be avoided.

In this paper, two models for associative memory based on a measure of manhattan length are proposed. First, we propose the two-layered model which has an advantage to its implementation by using PDN. We also refer to the way to improve the recalling ability of this model against noisy input patterns. Secondly, we propose the other model which always recalls the nearest memory pattern in a measure of manhattan length by lateral inhibition. Even if a noise of input pattern is so large that the first model can not recall, this model can recall correctly against such a noisy pattern. We also confirm the performance of the two models by computer simulations.

This article analyzes the property of the fully interconnected neural networks as a method of solving combinatorial optimization problems in general. In particular, in order to escape local minimums in this model, we analyze theoretically the relation between the diagonal elements of the connection matrix and the stability of the networks. It is shown that the position of the global minimum point of the energy function on the hyper sphere in n dimensional space is given by the eigen vector corresponding the maximum eigen value of the connection matrix. Then it is shown that the diagonal elements of the connection matrix can be improved without loss of generality. The equilibrium points of the improved networks are classified according to their properties, and their stability is investigated. In order to show that the change of the diagonal elements improves the potential for the global minimum search, computer simulations are carried out by using the theoretical values. In according to the simulation result on 10 neurons, the success rate to get the optimum solution is 97.5%. The result shows that the improvement of the diagonal elements has potential for minimum search.

The authors propose a model of the top down parser for continuous speech recognition. It utilizes a subject of an input sentence for its top down process and a preceding transition among subjects for the determination of a new subject. A task, a washing machine operation, which has five subjects are examined.

This study proposes a new training method for hidden Markov model with separate vector quantization (SVQ-HMM) in speech recognition. The proposed method uses the correlation of two different kinds of features: cepstrum and delta-cepstrum. The correlation is used to decrease the number of reestimation for two features thus the total computation time for training models decreases. The proposed method is applied to Japanese language isolated dgit recognition.

A new algorithm for timing driven placement based on the fuzzy theory is proposed. In this method, the signal delay on the longest path, the chip area and the total wire length can be simultaneously minimized. Introducing the probability measures of fuzzy events, falling down into the local optimal solutions can be avoided. At first, we define the fuzzy placement relation using the graph distance matrix and fuzzy distance relation matrix, and we give a new placement method based on the fuzzy placement relation and the probability measures of fuzzy events. Secondly, we extend this placement method so as to apply to the timing driven placement problem by introducing a fuzzy membership functions which represent the signal delay on the longest path and the chip area. Finally, experimental results are shown to compare our method with one of the previous methods.

Recently, the hardware realizations of the neural networks for specially-purposed-use have been in focus. In this paper, two kinds of networks, a two-layer network and the Boltzmann machine, using the switched-capacitor circuit are proposed. The variable synaptic weights of neural circuit are realized by through the programmable capacitor array (PCA) in the switched-capacitor variable-coefficients multiplier. As a result, the recognition system of the handwritten character using a two-layer neural network is constructed by the discrete electronic elements and its desirable effects are shown by the experimental results. The stochastic operation in the processing element (PE) of the Boltzmann machine is realized by using the generation of noise voltage with the random number and is also confirmed by teh experimental results using the discrete electronic elements. Furthermore, the operations of the PE have been also confirmed by using the simulation of Traveling-Salesman Problem.