Mitsubishi Denki Kabushiki Kaisha

Shuichi Tai

Kazuo Kyuma

Masaya Oita

Jun Ohta

Masahiro Yamaguchi

Nagaaki Ohyama

Masanobu Takahashi

Eiichi Funatsu

Kunihiko Hara

Yoshikazu Nitta

Takashi Toyoda

Toshio Shinnishi

Keisuke Kojima

Yuichi Koshiba

Eberhard Lange

An apparatus for sensing and processing images is provided with a photo detector array arranged in a matrix form, a control circuit for feeding a row of the array with voltage for sensitivity control, and a neural network for processing current flowing from a column of the array to the ground in order to obtain an apparatus for sensing and processing images having a simple configuration, a high frame speed, the capability of forming a focus of attention, and high throughput of data and possibility of connecting to the neural network.

Apparatus and method for sensing and processing images

A learning method for a neural network, in which at least a portion of the interconnection strength between neurons takes discrete values, includes the steps of updating an imaginary interconnection strength taking continuous values by using the quantity of update of the interconnection strength which has been calculated by using the discrete interconnection strength, and discretizing the imaginary interconnection strength so as to provide a novel interconnection strength.

Learning method for neural network having discrete interconnection

A photodetector has a semiconductor substrate which produces light-induced charge upon the absorption of incident light. A first electrode and a second electrode are attached to the surface of the semiconductor substrate so as to form metal-semiconductor junctions. When control voltage V.sub.B, which is variable in a positive range through a negative range, is applied to the first electrode, a photocurrent flows through the second electrode and depletion layers are formed in the surface of the semiconductor substrate. The control voltage V.sub.B applied to the first electrode increases the expanse of one of the depletion layers relative to that of the other to cause the light-induced charge to drift toward one of the depletion layers or the other. Consequently, a positive or negative current is delivered through the second electrode. Thus, the photosensitivity of the photodetector can be controlled by the control voltage V.sub.B.

Photodetector, a photodector array comprising photodetectors, an object

An information retrieval system allowing the user to build a database or to retrieve data therefrom based on vague retrieval-designating data without becoming aware of the database structure. The system comprises a neural network, a memory, an interface part and a CRT. The neural network stores data designating electronic still pictures contained in the memory. When data for designating retrieval are input, the interface part groups the data into such categories as the place where the desired picture was taken and the date on which it was taken, and supplies the neural network with the categorized input data. In turn, the neural network outputs by association the data corresponding to the input data. Given the data from the network, the memory outputs the relevant electronic still picture to the CRT for display.

Information retrieval system

An intelligence information processing system is composed of an associative memory and a serial processing-type computer. Input pattern information is associated with the associative memory, and pattern recognition based on the computer evaluates an associative output. In accordance with this evaluation, an associative and restrictive condition is repeatedly added to the energy function of a neural network constituting the associative memory, thereby converging the associative output on a stable state of the energy. The converged associative output is verified with intelligence information stored in a computer memory. The associative and restrictive condition is again repeatedly added to the energy function in accordance with the verification so as to produce an output from the system.

Intelligence information processing method

A data processing apparatus having one or more processors each comprising an optical vector matrix multiplier and its peripheral circuits mounted on a single semiconductor substrate, the multiple processors constituting a network. The components of the optical vector matrix multiplier may be divided on two semiconductor substrates so that light-borne data is exchanged therebetween. These arrangements provide a compact multifunction data processing apparatus adapted to deal flexibly with diverse computing problems.

Data processing apparatus with optical vector matrix multiplier and

The knowledge information processing system includes a first and second associative memory unit groups. The associative memory units of the first associative memory unit group 1 associates a plurality of distinct features to the input pattern 20. In response to the combination of associated outputs from the first associative memory unit group 1, the second associative memory unit group 4 evaluates and associates features corresponding to those associated by the first associative memory unit group 1. The logical operation unit group 6 compares the associated outputs of the first associative memory unit group 1 with those of the second to judge whether or not corresponding associated outputs agree with each other. If the corresponding associated outputs do not agree, the logical operation unit group 6 outputs feedback information items for correcting the energy functions of the first associative memory unit group 1, thereby repeating the association and the evaluation process.

Knowledge information processing system including two associative memory

Intelligence information processing system

An optical computer for performing product and/or sum operations on input vector information and matrix information includes an array of light emitting elements, the array having a plurality of columns and a plurality of rows. Input circuitry is provided for supplying input vector information to the array while matrix circuitry is provided for dynamically applying matrix information to the array. Logic circuitry is provided for performing one of a logical product and a logical sum operation on the input vector information and the matrix information and for generating an output thereof.

Optical neurocomputer with dynamic weight matrix

An optical neural network which imitates a biological neural network, to provide an associative and/or pattern recognition function, is made of light emitting elements to represent an input neuron state vector, a correlation matrix which modulates light according to stored vector information, light receiving elements, an accumulator and a comparator to perform a threshold function. A stored vector closest to an input vector can be found from a large amount of information without increasing the system size by dividing the correlation matrix and the input neuron state vector with time division techniques, frequency modulation or phase modulation techniques. Positive and negative valves can also be provided with similar techniques.

Growing community of inventors

Hyogo, Japan

Shuichi Tai