查詢結果分析
相關文獻
- Fault Tolerant Training of Eeedforward Neural Networks
- Applying Hashing Search and Fuzzy Fault-Tolerant Algorithms for the Fast Recognition of Multi-Font Printed Chinese Characters
- 模糊性拜占庭協議[Byzantine Agreement]初探
- 使用切換網路設計容錯多級交連網路
- 開發一個容錯資料庫系統
- On Finding Node-Disjoint Parallel Paths in Rotator Graphs
- Fault-Tolerant Q-Ary K-Cube Networks by Adding Extra Dimensions Based on Coding Theory
- Parallel Routing Paths in Chordal Rings
- A Fault-Tolerant Model for Replication in Distributed-File Systems
- Nondominated (K, M)-Coteries for the K-out of-M Resources Allocation Problme
頁籤選單縮合
題 名 | Fault Tolerant Training of Eeedforward Neural Networks=前饋式神經網路的容錯訓練 |
---|---|
作 者 | 佘步雲; 謝文雄; | 書刊名 | Proceedings of the National Science Council : Part A, Physical Science and Engineering |
卷 期 | 23:5 1999.09[民88.09] |
頁 次 | 頁599-608 |
分類號 | 312.2 |
關鍵詞 | 前饋式神經網路; 容錯; Feedforward networks; Fault tolerance; Backpropagation; Output nodes saturation; Constraint backpropagation; |
語 文 | 英文(English) |
英文摘要 | Fault tolerance is one of the key performance measures of artificial neural networks (ANN's) and is often viewed as an inherent feature of ANN's. But without precise designing, it is not able to guarantee the degree of fault tolerance. This paper presents an extensive study on the fault tolerant property of feedforward neural networks. We propose a constraint backpropagation (CBP) training method, which can guarantee a high degree of fault tolerance when one or two hidden nodes fail. In order to achieve the goal of fault tolerance, we define an energy term, called constraint energy, that measures the performance degradation when some hidden nodes fail. During training, both the normal energy and the constraint energy will be minimized. We also develop a simple technique called output node saturation (ONS). By incorporating CBP with ONS, we can find a network which maintains exactly the same performance as a normal network when some hidden nodes fail. Experimental results show that a network trained by CBP also possess better generalization properties than does one trained by normal backpropagation (BP). |
本系統中英文摘要資訊取自各篇刊載內容。