一种具有容错能力的自适应神经网络分类器

AN ADAPTIVE FAULT TOLERANT NEURAL NETWORK CLASSIFIER

在国内外容错型神经网络研究的基础上 ,提出了一种具有容错能力的自适应神经网络 FTART4.该算法针对解决多点断路故障容错性的难点 ,提出了一种独特的增加网络冗余的方法 ,通过确定故障敏感点达到了冗余度与容错性的平衡 .同时对 FTART4神经网络解决多点断路故障问题进行了严谨的形式化分析 ,给出了 FTART4算法的完整描述 .采用通用的神经网络测试数据对算法进行了测试 。

Based on the research of fault tolerant neural networks by some precursors, an adaptive fault tolerant neural networks learning algorithm FTART4 is proposed to resolve the multi node open fault problem. FTART4 uses a distinct mechanism to deal with the dilemma of fault tolerance and redundance by ascertaining a fault sensitive parameter. The problem's formalization and the specific FTART4 algorithm are given. By applying the FTART4 to some standard benchmarks, the experitments show that this method achieves preferable results.