US 5,479,569 AGranted

Intelligence information processing method

AssigneeMitsubishi Denki Kabushiki Kaisha

InventorsKazuo Kyuma, Shuichi Tai, Jun Ohta, Masaya Oita, Nagaaki Ohyama, Masahiro Yamaguchi

Life of this patent

Estimating the term…

Loading patent…

Abstract

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.

Claims30

Dependent claims

A method for processing an input sequence of elements for comparison with a predetermined set of sequences of a predetermined set of elements, comprising the steps of:

(a) applying the input sequence of elements to an input of an associative memory comprising a neural network;
(b) obtaining an associated output sequence of elements from the associative memory;
(c) evaluating each element of the associated output sequence of elements to determine whether each element is a member of the predetermined set of elements;
(d) improving the energy function of the neural network in response to a determination that an element is not in the predetermined set of elements;
(e) repeating the steps of applying and evaluating in response to a determination that an element is not in the predetermined set, applying the element as the input to the associative memory;
(f) evaluating the associated output sequence of elements to determine whether the associated output sequence is a member of the predetermined set of sequences;
(g) improving the energy function of the neural network in response to a determination that the associated sequence is not in the predetermined set of sequences;
and
(h) repeating the step of applying and the steps of and evaluating in response to a determination that the associated sequence is not in the predetermined set of sequences, applying the input sequence of elements to the associated memory.

6 more elements

A method for processing an input signal representative of a sequence of physical elements for comparison with a predetermined set of sequences of a predetermined set of elements, comprising the steps of:

(a) applying the input signal to an input of an associative memory device comprising a neural network having an energy function;
(b) obtaining an associated output signal representative of an associated output sequence of elements from the associative memory device;
(c) evaluating each element of the associated output sequence of elements to determine whether each element is a member of the predetermined set of elements;
(d) improving the energy function of the neural network in response to a determination that an element is not in the predetermined set of elements;
(e) repeating the steps of applying and evaluating in response to a determination that an element is not in the predetermined set, applying an input signal representative of the element which is not in the predetermined set to the associative memory device;
(f) evaluating the associated output sequence of elements to determine whether the associated output sequence is a member of the predetermined set of sequences;
(g) improving the energy function of the neural network in response to a determination that the associated sequence is not in the predetermined set of sequences;
and
(h) repeating the step of applying the steps of and evaluating in response to a determination that the associated sequence is not in the predetermined set of sequences, applying an input signal representative of the input sequence of elements to the associated memory device.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 08/056,055Filed 30 Apr 1993 · continuation
Priority: JP 2-25933226 Sep 1990
Granted: 26 Dec 1995
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G06N 3/02
Computing arrangements based on biological models: neural networks
G06N 3/042
Architecture, e.g. interconnection topology: knowledge-based neural networks; Logical representations of neural networks
G06N 3/044
Architecture, e.g. interconnection topology: recurrent networks, e.g. Hopfield networks
G06N
AI and machine learning