JPS6482133A - Network learning system - Google Patents

Network learning system

Info

Publication number
JPS6482133A
JPS6482133A JP62240095A JP24009587A JPS6482133A JP S6482133 A JPS6482133 A JP S6482133A JP 62240095 A JP62240095 A JP 62240095A JP 24009587 A JP24009587 A JP 24009587A JP S6482133 A JPS6482133 A JP S6482133A
Authority
JP
Japan
Prior art keywords
neurons
learning
dead
neural network
active
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP62240095A
Other languages
Japanese (ja)
Inventor
Kazuhiko Ono
Katsunobu Fushikida
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP62240095A priority Critical patent/JPS6482133A/en
Publication of JPS6482133A publication Critical patent/JPS6482133A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Analysis (AREA)

Abstract

PURPOSE:To improve the learning ability by initializing again a neuron which is calmed in a learning process. CONSTITUTION:When the rapid learning is carried out, some neurons 1 become unbearable to the conflict of the learning data and are calmed down. Then it is regarded that these neurons are dead in case the output is kept extremely minute for a fixed period of time. Thus the death of those neurons 1 are decided and the synapses 2 connected to the dead neurons 1 are all initialized for new lives of neurons 1. Thus the neurons 1 dies once are active again and the number of active neurons 1 are increased in a neural network as a whole. Then the efficiency of the neural network is improved.
JP62240095A 1987-09-24 1987-09-24 Network learning system Pending JPS6482133A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP62240095A JPS6482133A (en) 1987-09-24 1987-09-24 Network learning system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP62240095A JPS6482133A (en) 1987-09-24 1987-09-24 Network learning system

Publications (1)

Publication Number Publication Date
JPS6482133A true JPS6482133A (en) 1989-03-28

Family

ID=17054416

Family Applications (1)

Application Number Title Priority Date Filing Date
JP62240095A Pending JPS6482133A (en) 1987-09-24 1987-09-24 Network learning system

Country Status (1)

Country Link
JP (1) JPS6482133A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1990013874A1 (en) * 1989-05-06 1990-11-15 Yozan Inc. Data processing system
US5219054A (en) * 1991-02-27 1993-06-15 Tochigifujisangyo Kabushiki Kaisha Hub clutch device
US5402519A (en) * 1990-11-26 1995-03-28 Hitachi, Ltd. Neural network system adapted for non-linear processing
JP2017536635A (en) * 2015-07-31 2017-12-07 小米科技有限責任公司Ｘｉａｏｍｉ Ｉｎｃ． Picture scene determination method, apparatus and server

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1990013874A1 (en) * 1989-05-06 1990-11-15 Yozan Inc. Data processing system
US5402519A (en) * 1990-11-26 1995-03-28 Hitachi, Ltd. Neural network system adapted for non-linear processing
US5219054A (en) * 1991-02-27 1993-06-15 Tochigifujisangyo Kabushiki Kaisha Hub clutch device
JP2017536635A (en) * 2015-07-31 2017-12-07 小米科技有限責任公司Ｘｉａｏｍｉ Ｉｎｃ． Picture scene determination method, apparatus and server

Similar Documents

Publication Publication Date Title
Changeux Neuronal man: The biology of mind
Churchland Cognitive activity in artificial neural networks
Myers Avoidance learning as a function of several training conditions and strain differences in rats.
ATE6032T1 (en) BIOLOGICALLY ACTIVE SUBSTANCES, THEIR PRODUCTION FROM HUMAN CASEIN AND PREPARATIONS CONTAINING THEM.
JPS6482133A (en) Network learning system
Robertson Rule based expert simulation environment.
EP0342017A3 (en) Inference processor using meta knowledge
Anderson et al. Retention of an incompletely learned avoidance response: Some problems with replication
McCain et al. PCE I: The effects of three reward magnitude shifts
Elmaghraby et al. Expert system for chemical process control.
Ridgers et al. Influence of amylobarbitone on operant depression and elation effects in the rat
Snyder Is Freud's model of the mind autopoietic?
Miramontes et al. Antichaos in ants: the excitability metaphor at two hierarchical levels
Coker et al. The effect of strychnine sulfate on maze learning as a function of task difficulty
Vol'fengagen et al. Models and methods for representing knowledge algebra on knowledge-manipulation frames.
Rolls et al. Neuronal networks in the brain
Yamamoto Modeling of hysteretic behavior with neural network and its application to non-linear dynamic response analysis.
Chapeau-Blondeau et al. Signal transcoding by nonlinear sensory neurons: information-entropy maximization, optimal transfer function, and anti-Hebbian adaptation
Nielsen The application of AI techniques to model maintenance.
Режабек MIND OF CELLS AND MODELING IN CYTOETOLOGY
SU769568A1 (en) Device for simulating population activity
UMARETIYA Specifications extraction and synthesis: Their correlations with preliminary design(Ph. D. Thesis)
PARAMONOV Certain problems in modeling nerve networks(Neuron networks modeling from viewpoint of intracellular and cell-medium interaction, discussing coding properties and nonsingular self adjusting system response)
Motomura et al. A Fundamental Study of Free Shape Forging. II. Simulation of Plane-Strain Free Shape Forging Processes
Fox Dynamic, Genetic And Chaotic Programming, The Sixth Generation by B. Souček and The IRIS Group, J. Wiley and Sons, Chichester, UK, 1992, xiii+ 567 pp., index (£ 71.00).