EP0362840A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Neural network system
Assignee: Toshiba Corp
•
Filing: 1989-10-05
•
Granted: —
•
Expires: 2009-10-05
Abstract
Abstract N neural networks (111) having different set-values are provided, where N is an integer greater than 2. Each neural network has plurality of artificial neurons and processes information. An optimal output detecting circuit (101, 121) receives outputs of the N neural networks (111) and determines the optimal one of the neural networks based on the outputs of the N neural networks. An output circuit (102) receives and outputs the output of the neural network detected by the optimal output detecting circuit (101, 102).
Inventors
- 👤 Ryuichi C/O Intellectual Property Division Kuwata
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 14:01
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/045; G06N3/06; G06N3/063
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
82 words
A neural network system comprising: N neural network means (111) having different set-values, where N is an integer greater than 2, each having plurality of artificial neurons and for processing information; detecting means (101, 121) for receiving outputs of said N neural network means and detecting the optimal one of the neural network means based on the outputs of the neural network means; and output means (102) for receiving and outputting the output of the neural networks detected by said detecting means.
Claim 2
Dependent Claim
82 words
A neural network system comprising: N neural network means (111) having different set-values, where N is an integer greater than 2, each having plurality of artificial neurons and for processing information; detecting means (101, 121) for receiving outputs of said N neural network means and detecting the optimal one of the neural network means based on the outputs of the neural network means; and output means (102) for receiving and outputting the output of the neural networks detected by said detecting means.
Claim 3
Dependent Claim
78 words
The neural network system according to claim 1, characterized in that said detecting means includes means (101, 121) for receiving the outputs of said N neural network means, obtaining energy function values of the N neural networks, comparing the energy function values, and determining the neural network means having the minimum energy function value, and said output means includes means (102) for selecting and outputting the output of the neural network means having the minimum energy function value.
Claim 4
Dependent Claim
28 words
The neural network system according to claim 2, characterized in that said detecting means includes means (103) for scanning the outputs of said N neural network means (111).
Claim 5
Dependent Claim
74 words
A neural network system comprising: neural network means (201) for receiving a plurality of input signals and outputting a signal for detecting any input signal which is at a desired level; signal supplying means (204) for supplying the input signals to said neural network means (204); and signal detecting means (202) for detecting any input signal that is at the desired level, in accordance with the signal output from said neural network means (201).
Claim 6
Dependent Claim
74 words
A neural network system comprising: neural network means (201) for receiving a plurality of input signals and outputting a signal for detecting any input signal which is at a desired level; signal supplying means (204) for supplying the input signals to said neural network means (204); and signal detecting means (202) for detecting any input signal that is at the desired level, in accordance with the signal output from said neural network means (201).
Claim 7
Dependent Claim
46 words
The neural network system according to claim 4, characterized in that said signal supplying means includes means (204) for stopping the supply of the input signal to said neural network, said input signal been detected by said signal detecting means to be at the desired level.
Claim 8
Dependent Claim
99 words
The neural network system according to claim 4, characterized by further comprising: reversing means (206) for reversing the order in which said input signals have been placed in terms of signal level; second neural network means (211) connected to said reversing means (206), for receiving signals output from said reversing means (206) and outputting a signal for detecting any input signal at the desired level; and second signal detecting means (212) for detecting any input signal output from said reversing means (206) that is at the desired level, in accordance with an output of said second neural network (211).
Claim 9
Dependent Claim
77 words
The neural network system according to claim 4, characterized in that said signal supplying means comprises: reversing means (206) for the order in which said input signals have been placed in terms of level; and switching means (207) connected to said reversing means (206) and said neural network means (201), for selecting the input signals (I1 to IN) or the signals output from said reversing means, and supplying the signals, thus selected, to said neural network means.
Claim 10
Dependent Claim
71 words
The neural network system according to claim 4, characterized in that said signal supplying means comprises: converting means (216) for receiving a plurality of signals and converting these signals to complement signals at levels complement to a specified level range; multiplying means for multiplying said signals by the complement signals output from said converting means; and output means (210) for supplying signals output by said multiplying means, to said neural network.
Claim 11
Dependent Claim
50 words
A neural network system comprising: a plurality of artificial neurons (311) arranged in rows and columns, connected to one another, and divided into hierarchical groups so that the artificial neurons of each hierarchial group have readiness of ignition which is different from that of those of any other hierarchial group.
Claim 12
Dependent Claim
50 words
A neural network system comprising: a plurality of artificial neurons (311) arranged in rows and columns, connected to one another, and divided into hierarchical groups so that the artificial neurons of each hierarchial group have readiness of ignition which is different from that of those of any other hierarchial group.
Claim 13
Dependent Claim
60 words
The neural network system according to claim 9, characterized in that the rows or columns of artificial neurons are assigned to events, respectively, and the columns or rows of artificial neurons are assigned to the priorities of the events, so that an order in which the events should take place is determined by processing signals output from the artificial neurons.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.