Improvement of Recognition Performance for the Fuzzy ARTMAP Using Average Learning and Slow Learning
スポンサーリンク
概要
- 論文の詳細を見る
A new learning method is proposed to enhance the performances of the fuzzy ARTMAP neural network in the noisy environment. It combines the average learning and slow learning for the weight vectors in the fuzzy ARTMAP. It effectively reduces a category proliferation problem and enhances recognition performance for noisy input patterns.
- 社団法人電子情報通信学会の論文
- 1998-03-25
著者
-
Lee C
Seoul Nat'l Univ. Seoul Kor
-
Lee Choong
Department Of Electronics Engineering Seoul National University
-
Lee Jae
The Department Of Neurosurgery Pusan National University School Of Medicine
-
Lee Choong
The Department of Electronics Engineering, Seoul National University
-
YOON Chan
School of Electrical Engineering, Dongyang Technical College
-
YOON Chan
the Department of Electronic Communication Engineering, Dongyang Technical College
-
Lee Jae
The Department Of Computer Science Hallym University
-
Lee Choong
The Department Of Electronics Engineering Seoul National University
-
Yoon C
School Of Electrical Engineering Dongyang Technical College
-
Yoon Chan
The Department Of Electronics Engineering Seoul National University
-
Lee J
School Of Electrical Engineering Dongyang Technical College
関連論文
- Improvement of Noise Tolerance in Fuzzy ART Using a Weighted Sum and a Fuzzy AND Operation
- Digital Logic Implementation of Wide-Range Frequency Linear Detector
- Improvement of Recognition Performance for the Fuzzy ARTMAP Using Average Learning and Slow Learning
- 24-4 Linear and Nonlinear Interpolation Filters for Interlaced to Progressive Conversion
- An Incoherent Direct-Conversion Receiver with a Full Digital Logic FSK Demodulator
- Blind Algorithm for Decision Feedback Equalizer
- Microwave Properties of Sapphire Resonators with a Gap and Their Applicability for Measurements of the Intrinsic Surface Impedance of Thin Superconductor Films( Superconducting High-frequency Devices)
- Delayed Hyponatremia Following Transsphenoidal Surgery for Pituitary Adenoma
- Block Loss Recovery using Sequential Projections onto the Feature Vectors
- An Efficient Encoding of DCT Blocks with Block-Adaptive Scanning : PAPER Special Issue on Digital Broadcasting Technology (Special Issue on Digital Broadcasting Technology)
- Phase/Frequency Modulation Combined with Multilevel Block Codes
- Image Compression by Vector Quantization of Projection Data
- Modification of LZSS by Using Structures of Hangul Characters for Hangul Text Compression
- Adaptive Resource Allocation for a Two-Way OFDM Relay Network with Fairness Constraints