Back-Propagation Learning Algorithm with Learning Coefficient which Changes by the Sum of the Squared Error for the Output Layer
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we propose a fast learning algorithm for the multi-layered neural network which changes the learning coefficient for the hidden units (used to a fixed parameter in general) by the sum of the square error for the output units. The algorithm is able to accelerate learning by selecting appropriately the ratio of the learning accerelation coefficient to the learning continuation one defined in the paper. The proposed algorithm is an extention of conventional back-propagation learning algorithm. This learning algorithm makes more acceleration possible of learning, one of weak points on back-propagation. The effectiveness of this method on convergence of the sum of the square error for the output units has been verified by the computer simulation for two examples of an exclusive-or problem and an encoding one using the proposed learning algorithm.
- 東海大学の論文
著者
関連論文
- Anorectal Agenesis with a Rectourethral Fistula Diagnosed in an Adult : Report of a Case
- A Design for Three-Valued Logical Function with Negative Gates
- Gastrointestinal Stromal Tumor Arising in the Pelvic Cavity : A Case Report
- Muscle Strength and Walking Ability After Laparoscopic Hernioplasty Versus Conventional Repair
- Monotone Decomposition of Three Valued Logical Function and It's Implementation
- Buccal administration of dexmedetomidine as a preanesthetic in children
- 科学技術開発のカオス予測法 : そのプログラム構成法
- Back-Propagation Learning Algorithm with Dynamic Learning Coefficient by Introducing Fuzzy Inference
- Umbilical approach using the sliding-window method to avoid a large abdominal incision : report of two pediatric cases
- Back-Propagation Learning Algorithm with Learning Coefficient which Changes by the Sum of the Squared Error for the Output Layer
- A Learning Algorithm with the Variation Rate of Error for Multi-layered Neural Networks