In this paper, we proposes a novel fuzzy control for parameter scheduling of the Hopfield neural network. When a combinatorial optimization problem, such as the traveling salesman problem, is solved by Hopfield neural network, it is efficient to adaptively change the parameters of the energy function and sigmoid function. By changing the parameters on purpose, this network can avoid being trapped at a local minima. Since there exists complex relations among these parameters, it is difficult to analytically determine the ideal scheduling. First, we investigate a bad scheduling to change parameters by simple experiments and find several rules that may lead to a good scheduling. The rules extracted from the experimental results are then realized by fuzzy control. By using fuzzy control, we can judge bad scheduling from vague network stages, and then correct the relations among the parameters. Computer simulation results of the Traveling Salesman Problem (TSP) is considered as an example to demonstrate its validity.

In computer vision, the interpretation of 3D motion of an object in the physical world is an important task. This study proposes a 3D motion interpretation method which uses a neural network system consisting of three kinds of neural networks. This system estimates the solutions of 3D motion of an object by interpreting three optical flow (OF-motion vector field calculated from images) patterns obtained at the different view points for the same object. In the system, OF normalization network is used to normalize diverse OF patterns into the normalized OF format. Then 2D motion interpretation network is used to interpret the normalized OF pattern and to obtain the object's projected motion onto an image plane. Finally, 3D motion interpretation network totally interprets the three sets of the projected motions and it derives the solutions of the object's 3D motion from the inputs. A complex numbered version of the back-propagation (Complex-BP) algorithm is applied to OF normalization netwerk and to 2D motion interpretation network, so that these networks can learn graphical patterns as complex numbers. Also a 3D vector version of the back-propagation (3DV-BP) algorithm is applied to 3D motion interpretation network so that the network can learn the spatial relationship between the object's 3D motion and the corresponding three OF patterns. Though the interpretation system is trained for only basic 3D motions consisting of a single motion component, the system can interpret unknown multiple 3D motions consisting of several motion components. The generalization capacity of the proposed system was confirmed using diverse test patterns. Also the robustness of the system to noise was probed experimentally. The experimental results showed that this method has suitable features for applying to real images.

We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.

This paper discusses a digital neuroprocessor named Quantizer Neuron Chip (QNC) employing the Quantizer Neuron model and two newly developed schemes; "concurrent processing of quantizer neuron" and "removal of ineffective calculations". QNC simulates neural networks named the Multi-Functional Layered Network (MFLN) with 64 output neurons, 4672 quantizer neurons and two million synaptic weights and can be used for character or image recognition and learning. The processing speed of the chip achieved 1.6 µseconds per output neuron for recognition and 20 million connections updated per second (MCUPS) for learning. In addition, QNC can execute multichip operation for increasing the size of networks. We applied QNC to handwritten numeral recognition and realized high speed recognition and learning. QNC is implemented in a 1.2 µm double metal CMOS with sea of gates' technology and contains 27,000 gates on a 10.9910.93 mm2 chip.

The paper describes the architecture and the simulated performances of a memory-based chip that emulates human cortical processing in early visual tasks, such as texture segregation. The featural elements present in an image are extracted by a convolution block and subsequently processed by the cortical chip, whose neurons, organized into three layers, gain relational descriptions (intelligent processing) through recurrent inhibitory/excitatory interactions between both inter-and intra-layer parallel pathways. The digital implementation of this architecuture directly maps the set of equations determining the status of the cortical network to achieve an optimal exploitation of VLSI technology in neural computation. Neurons are mapped into a memory matrix whose elements are updated through a programmable computational unit that implements synaptic interconnections. By using 0.5 µm-CMOS technology, full cortical image processing can be attained on a single chip (2020 mm2 die) at a rate higher than 70 frames/second, for images of 256256 pixels.

An integrated pen interface system was developed to allow effective Japanese text entry. It consists of sub-systems for handwriting recognition, contextual post-processing, and enhanced Kana-to-Kanji conversion. The recognition sub-system uses a hybrid algorithm consisting of a pattern matcher and a neural network discriminator. Special care was taken to improve the recognition of non-Kanji and simple Kanji characters frequently used in fast data entry. The post-processor predicts consecutive characters on the basis of bigrams modified by the addition of parts of speech and substitution of macro characters for Kanji characters. A Kana-to Kanji conversion method designed for ease of use with a pen interface has also been integrated into the system. In an experiment in which 2,900 samples of Kanji and non-Kanji characters were obtained from 20 subjects, it was observed that the original recognition accuracy of 83.7% (the result obtained by using the pattern matching recognizer) was improved to 90.7% by adding the neural network discriminator, and that it was further improved to 94.4% by adding the post-processor. The improved recognition accuracy for non-Kanji characters was particularly marked.

In cellular mobile systems, an alternative approach for a Dynamic Channel Assignment problem is presented. It adaptively assigns the channels considering the cochannel interference level. The Dynamic Channel Assignment problem is modeled on the different cellular system from the conventional one. In this paper, we formulate the rearrangement problem in the Dynamic Channel Assignment and propose a novel strategy for the problem. The proposed algorithm is based on an artificial neural network as a specific dynamical system, and is successfully applied to the cellular system models. The computer simulation results show that the algorithm utilized for the rearrangement is an effective strategy to improve the traffic characteristics.

A very-high-speed ten-neuron analog neural network LSI chip is fabricated for the first time using super self-aligned Si bipolar process technology. The LSI consists of ten neurons and 100 electrically modifiable synaptic weights. The neural network nonlinear mapping function to solve the four-bit parity problem is successfully demonstrated at 150 mega-patterns/sec. The operation speed of this neural network is, to the best of the authors, knowledge, the fastest yet reported.

Artificial Neural Networks (ANN's) that are able to learn exhibit many interesting features making them suitable to be applied in several fields such as pattern recognition, computer vision and so forth. Learning a given input-output mapping can be regarded as a problem of approximating a multivariate function. In this paper we will report a theoretical framework for approximation, based on the well known sequences of functions named approximate identities. In particular, it is proven that such sequences are able to approximate a generally continuous function to any degree of accuracy. On the basis of these theoretical results, it is shown that the proposed approximation scheme maps into a class of networks which can efficiently be implemented with analog MOS VLSI or BJT integrated circuits. To prove the validity of the proposed approach a series of results is reported.

A pseudoinverse rule, one of major rule to determine a weight matrix for associative memory, has large capacity comparing with other determining rules. However, it is wellknown that the rule has small domains of attraction of memory vectors on account of many spurious states. In this paper, we try to improve the problem by means of subtracting a constant from all diagonal elements of a weight matrix. By this method, many spurious states disappear and eigenvectors with negative eigenvalues are introduced for the orthocomplement of the subspace spanned by memory vectors. This method can be applied to two types of networks: binary network and analog network. Some computer simulations are performed for both two models. The results of the simulations show our improvement is effective to extend error correcting ability for both networks.

This paper describes a novel technique to realize high performance digital sequential circuits by using Hopfield neural networks. For an example of applications of neural networks to digital circuits, a novel gate circuit, full adder circuit and latch circuit using neural networks, which have the global convergence property, are proposed. Here, global convergence means that the energy function is monotonically decreasing and each circulit always operates correctly independently of the initial values. Finally the several digital sequential circuits such as shift register and asynchronous binary counter are designed.

Pitch frequency is a basic characteristic of human voice, and pitch extraction is one of the most important studies for speech recognition. This paper describes a simple but effective technique to obtain correct pitch frequency from candidates (pitch candidates) extracted by the short-range autocorrelation function. The correction is performed by a neural network in consideration of the time coutinuation that is realized by referring to pitch candidates at previous frames. Since the neural network is trained by the back-propagation algorithm with training data, it adapts to any speaker and obtains good correction without sensitive adjustment and tuning. The pitch extraction was performed for 3 male and 3 female announcers, and the proposed method improves the percentage of correct pitch from 58.65% to 89.19%.

This paper presents a structure of adaptive equalizer equipped with a neural network and a Viterbi decoder, and evaluates its performance under a fading environment by means of computer simulation.

The data-driven model of computation is well suited for flexible and highly parallel simulation of neural networks. First, the operational semantics of data-driven languages preserve the locality and functionality of neural networks, and naturally describe their inherent parallelism. Second, the asynchronous data-driven execution facilitates the implementation of large and scalable multiprocessor systems, which are necessary to obtain considerable degrees of simulation sppedups. In this paper, we present a dynamic data-driven multiprocessor system, and demonstrate its suitability for the paralel simulation of back propagation neural networks. Two parallel implementations are described and evaluated using an image data compression network. The system is scalable, and as a result, the performance improved proportionally with the increase in number of processors.

In this paper, a middle-mapping learning algorithm for cellular associative memories is presented. This algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the ourter product method. It can guarantee each prototype is stored at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.

We have aimed at constructing a forward dynamics model (FDM) of the human arm in the form of an artificial neural network while recordings of EMG and movement trajectories. We succeeded in: (1) estimating the joint torques under isometric conditions and (2) estimating trajectories from surface EMG signals in the horizontal plane. The human arm has seven degrees of freedom: the shoulder has three, the elbow has one and the wrist has three. Only two degrees of freedom were considered in the previous work. Moreover, the arm was supported horizontally. So, free movement in 3D space is still a necessity. And for 3D movements or posture control, compensation for gravity has to be considered. In this papre, four joint angles, one at the elbow and three at the shoulder were estimated from surface EMG signals of 12 flexor and extensor muscles during posture control in 3D space.

This paper proposes an approach for approximately realizing nonlinear mappings of interval vectors by interval neural networks. Interval neural networks in this paper are characterized by interval weights and interval biases. This means that the weights and biases are given by intervals instead of real numbers. First, an architecture of interval neural networks is proposed for dealing with interval input vectors. Interval neural networks with the proposed architecture map interval input vectors to interval output vectors by interval arithmetic. Some characteristic features of the nonlinear mappings realized by the interval neural networks are described. Next, a learning algorithm is derived. In the derived learning algorithm, training data are the pairs of interval input vectors and interval target vectors. Last, using a numerical example, the proposed approach is illustrated and compared with other approaches based on the standard back-propagation neural networks with real number weights.

In this paper, we develop a unified synthesizing approach for the cloning templates of Cellular Neural Networks (CNNs). In particular, we shall consider the case when the signal processing problem is complex, and a multilayered CNN with time-variant templates is necessary. The method originates from the existence of correspondence between the cloning templates of Cellular Neural Network and its discrete counterpart, Discrete-Time Cellular Neural Network (DTCNN), in solving a prescribed image processing problem when time-variant templates are involved. Thus, one can start with calculating the cloning templates from DTCNN, and then translating the cloning templates to those for CNN operations. As a result, the mathematical tools being used in the synthesis of Discrete-time Cellular Neural Network can also be applied to the analog type Cellular Neural Network. This inevitably helps to simplify the design problem of CNN for signal processing. Examples akin to contour drawing and parallel thinning are shown to illustrate the merits of our proposed method.

The number of nodes in a hidden layer of a feed-forward layered network reflects an optimality condition of the network in coding a function. It also affects the computation time and the ability of the network to generalize. When an arbitrary number of hidden nodes is used in designing the network, redundancy of hidden nodes often can be seen. In this paper, a method of reducing hidden nodes is proposed on the condition that a reduced network maintains the performances of the original network within an accepted level of tolerance. This method can be applied to estimate the performances of a network with fewer hidden nodes. The estimated performances indicate the lower bounds of the actual performances of the network. Experiments were performed using the Fisher's IRIS data, a set of SONAR data, and the XOR data for classification. The results suggest that sufficient number of hidden nodes, fewer than the original number, can be estimated by the proposed method.

Analysis of satellite images requires classificatio of image objects. Since different categories may have almost the same brightness or feature in high dimensional remote sensing data, many object categories overlap with each other. How to segment the object categories accurately is still an open question. It is widely recognized that the assumptions required by many classification methods (maximum likelihood estimation, etc.) are suspect for textural features based on image pixel brightness. We propose an image feature based neural network approach for the segmentation of AVHRR images. The learning algoriothm is a modified backpropagation with gain and weight decay, since feedforward networks using the backpropagation algorithm have been generally successful and enjoy wide popularity. Destructive algorithms that adapt the neural architecture during the training have been developed. The classification accuracy of 100% is reached for a validation data set. Classification result is compared with that of Kohonen's LVQ and basic backpropagation algorithm based pixel-by-pixel method. Visual investigation of the result images shows that our method can not only distinguish the categories with similar signatures very well, but also is robustic to noise.