An Analysis on Minimum Searching Principle of Chaotic Neural Network (Special Section of Selected Papers from the 8th Karuizawa Workshop on Circuits and Systems)
スポンサーリンク
概要
- 論文の詳細を見る
This article analyzes dynamics of the chaotic neural network and minimum searching principle of this network. First it is indicated that the dynamics of the chaotic neural network is described like a gradient descent, and the chaotic neural network can roughly find out a local minimum point of a quadratic function using its attractor. Secondly It is guaranteed that the vertex corresponding a local minimum point derived from the chaotic neural network has a lower value of the objective function. Then it is confirmed that the chaotic neural network can escape an invalid local minimum and find out a reasonable one.
- 社団法人電子情報通信学会の論文
- 1996-03-25
著者
-
Matsumiya Kazumichi
College Of Engineering University Of Osaka Prefecture:tokyo Institute Of Technology
-
OHTA Masaya
College of Engineering, University of Osaka Prefecture
-
OGIHARA Akio
College of Engineering, University of Osaka Prefecture
-
TAKAMATSU Shinobu
College of Engineering, University of Osaka Prefecture
-
FUKUNAGA Kunio
College of Engineering, University of Osaka Prefecture
-
Ogihara A
Osaka Prefecture Univ. Sakai‐shi Jpn
-
Ogihara Akio
College Of Engineering Osaka Prefecture University
-
Fukunaga K
Osaka Prefecture Univ. Sakai‐shi Jpn
-
Fukunaga Kunio
The Department Of Computer And Systems Sciences Osaka Prefecture University
-
Fukunaga Kunio
College Of Engineering Osaka Prefecture University
-
Ohta Masaya
College Of Engineering University Of Osaka Prefecture
-
Takamatsu Shinobu
College Of Engineering University Of Osaka Prefecture
関連論文
- An Analysis on Minimum Searching Principle of Chaotic Neural Network (Special Section of Selected Papers from the 8th Karuizawa Workshop on Circuits and Systems)
- A Study on Mouth Shape Features Suitable for HMM Speech Recognition Using Fusion of Visual and Auditory Information
- Speech Recognition Using HMM Based on Fusion of Visual and Auditory Information : Special Section of Letters Selected from 1994 IEICE Spring Conference
- Speech Recognition of lsolated Digits Using Simultaneous Generative Histogram (Special Section of Letters Selected from the 1993 IEICE Fall Conference)
- A Continuous Speech Recognition Algorithm Utilizing Island-Driven A^* Search (Special Section of Letters Selected from the 1993 IEICE Spring Conference)
- Asymmetric Neural Network and Its Application to Knapsack Problem
- An Improvement of the Pseudoinverse Rule with Diagonal Elements (Special Section of Papers Selected from JTC-CSCC'93)
- An Autocorrelation Associative Neural Network with Self-Feedbacks (Special Section of Letters Selected from the 1993 IEICE Fall Conference)
- A Neural Network with a Function of Inhibiting Subtours on TSP (Special Section of Letters Selected from the 1993 IEICE Fall Conference)
- Associative Neural Network Models Based on a Measure of Manhattan Length (Special Section on the 5th Karuizawa Workshop on Circuits and Systems)
- Speech Recognition Based on Fusion of Visual and Auditory Information Using Full-Frame Color Image (Special Section of Letters Selected from the 1996 IEICE General Conference)
- An Isolated Word Speech Recognition Using Fusion of Auditory and Visual Information (Special Section of Papers Selected from JTC-CSCC'95)
- Binary Neural Network with Negative Self-Feedback and Its Application to N-Queens Problem (Special Issue on Neurocomputing)
- A Theoretical Analysis of Neural Networks with Nonzero Diagonal Elements (Special Section on the 5th Karuizawa Workshop on Circuits and Systems)
- An Extraction Method of Lip Shape for Independent Speaker
- An Isolated Word Speech Recognition Based on Fusion of Visual and Auditory Information Using 30-frame/s and 24-bit Color Image (Special Section on Digital Signal Processing)
- Object Recognition in Image Sequences with Hopfield Neural Network
- A Correcting Method for Pitch Extraction Using Neural Networks (Special Section of Papers Selected from JTC-CSCC'93)
- Object Recognition Using Model Relation Based on Fuzzy Logic
- State Observers for Moore Machines and Generalized Adaptive Homing Sequences