Some problems in formal language theory are considered and are shown to be deterministic exponential time complete. They include the problems for a given context-free grammar G, a nondeterministic finite automaton M, a deterministic pushdown automaton M_D, of determining whether L(G)L(M), and whether L(M_D)L(M). Polynomial time reductions are presented from the pebble game problem, known to be deterministic exponential time complete, to each of these problems.

The Memory-Based Reasoning (MBR) is one of the mainstay approaches in massively parallel artificial intelligence research. However, it has not been explored from the viewpoint of hardware implementation. This paper demonstrates high robustness of the MBR, which is suitable for hardware implementation using Wafer Scale Integration (WSI) technology, and proposes a design of WSI-MBR hardware. The robustness is evaluated by a newly developed WSI-MBR simulator in the English pronunciation reasoning task, generally known as MBRTalk. The results show that defects or other fluctuations of device parameters have only minor impacts on the performances of the WSI-MBR. Moreover, it is found that in order to get higher reasoning accuracy, the size of the MBR database is much more crucial than the computation resolution. These features are proved to be caused by the fact that MBR does not rely upon each single data unit but upon a bulk data set. Robustness in the other MBR tasks can be evaluated in the same manner as discussed in this paper. The proposed WSI-MBR processor takes advantage of benefits discovered in the simulation results. The most area-demanding circuits--that is, multipliers and adders--are designed by analog circuits. It is expected that the 1.7 million processors will be integrated onto the 8-inch silicon wafer by the 0.3 µm SRAM technology.

This paper describes a text-independent speaker recognition method using predictive neural networks. For text-independent speaker recognition, an ergodic model which allows transitions to any other state, including selftransitions, is adopted as the speaker model and one predictive neural network is assigned to each state. The proposed method was compared to quantization distortion based methods, HMM based methods, and a discriminative neural network based method through text-independent speaker identification experiments on 24 female speakers. The proposed method gave the highest identification rate of 100.0%, and the effectiveness of predictive neural networks for representing speaker individuality was clarified.

A new method is proposed for automatically evaluating the English pronunciation quality of non-native speakers. It is assumed that pronunciation can be rated using three criteria: the static characteristics of phonetic spectra, the dynamic structure of spectrum sequences, and the prosodic characteristics of utterances. The evaluation uses speech recognition techniques to compare the English words pronounced by a non-native speaker with those pronounced by a native speaker. Three evaluation measures are proposed to rate pronunciation quality. (1) The standard deviation of the mapping vectors, which map the codebook vectors of the non-native speaker onto the vector space of the native speaker, is used to evaluate the static phonetic spectra characteristics. (2) The spectral distance between words pronounced by the non-native speaker and those pronounced by the native speaker obtained by the DTW method is used to evaluate the dynamic characteristics of spectral sequences. (3) The differences in fundamental frequency and speech power between the pronunciation of the native and non-native speaker are used as the criteria for evaluating prosodic characteristics. Evaluation experiments are carried out using 441 words spoken by 10 Japanese speakers and 10 native speakers. One half of the 441 words was used to evaluate static phonetic spectra characteristics, and the other half was used to evaluate the dynamic characteristics of spectral sequences, as well as the prosodic characteristics. Based on the experimental results, the correlation between the evaluation scores and the scores determined by human judgement is found to be 0.90.

We consider an asymptotically sparsely encoded associative memory. Patterns are encoded by n-dimensional vectors of 1 and 1 generated randomly by a sequence of biased Bernoulli trials and stored in the network according to Hebbian rule. Using a heuristic argument we derive the following capacities:c(n)n^e/4k log n'C(n)n^e/4k(1e)log n'where, 0e1 controls the degree of sparsity of the encoding scheme and k is a constant. Here c(n) is the capacity of the network such that any stored pattern is a fixed point with high probability, whereas C(n) is the capacity of the network such that all stored patterns are fixed points with high probability. The main contribution of this technical paper is a theoretical verification of the above results using the Poisson limit theorems of exchangeable events.

A discrete-time neuron model having a refractory period and containing a binary hysteresis output function is introduced. A detailed mathematical analysis of the output response is carried out and the necessary and sufficient condition which a sequence must satisfy in order to be designated as a periodic response of the neuron model under a constant or periodic stimulation is given.

The properties of the Haar Transform (HT) are discussed based on the Wavelet Transform theory. A system with two channels at resolution 2^-1 and 2^-2 for detecting paroxysm-spike in human's EEG is presented according to the multiresolution properties of the HT. The system adopts a coarse-to-fine strategy. First, it performs the coarse recognition on the 2^-2 channel for selecting the candidate of spike in terms of rather relaxed criterion. Then, if the candidate appears, the fine recognition on the 2^-1 channel is carried out for detecting spike in terms of stricter criterion. Three features of spike are extracted by investigating its intrinsic properties based on the HT. In the case of having no knowledge of prior probability of the presence of spike, the Neyman-Pearson criteria is applied to determining thresholds on the basis of the probability distribution of background and spike obtained by the results of statistical analysis to minimize error probability. The HT coefficients at resolution 2^-2 and 2^-1 can be computed individually and the data are compressed with 4:1 and 2:1 respectively. A half wave is regarded as the basic recognition unit so as to be capable of detecting negative and positive spikes simultaneously. The system provides a means of pattern recognition for non-stationary signal including sharp variation points in the transform domain. It is specially suitable and efficient to recognize the transient wave with small probability of occurrence in non-stationary signal. The practical examples show the performance of the system.

This paper presents a new algorithm for finding the kth-shortest paths between a specified pair of vertices in a directed graph with arcs having non-negative costs.

An adaptive algorithm is presented for fuzzy clustering of data. Partitioning is fuzzified by addition of an entropy term to objective functions. The proposed method produces more convex membership functions than those given by the fuzzy c-means algorithm.