首页>
外国专利>
DETERMINING INFLUENCE OF ATTRIBUTES IN RECURRENT NEURAL NET-WORKS TRAINED ON THERAPY PREDICTION
DETERMINING INFLUENCE OF ATTRIBUTES IN RECURRENT NEURAL NET-WORKS TRAINED ON THERAPY PREDICTION
展开▼
机译:确定属性在经过训练的递归神经网络中对治疗预测的影响
展开▼
页面导航
摘要
著录项
相似文献
摘要
A method and system of determining influence of attributes in Recurrent Neural Networks (RNN) trained on therapy prediction is provided. For each output neuron zkl a relevance score Rkl is decomposed into decomposed relevance scores Rk→jl for each component xjl of an input vector x1 and all decomposed relevance scores Rk→jl of the present step l are combined to a relevance score Rjl for the next step l−1.
展开▼
机译:提供了一种方法和系统,该方法和系统确定训练的递归神经网络(RNN)中的属性对治疗预测的影响。对于每个输出神经元z k Sub> l Sup>,相关性得分R k Sub> l Sup>分解为分解的相关性得分R k→ j Sub> l Sup>用于输入向量x 1 Sup的每个分量x j Sub> l Sup> >并且将当前步骤l的所有分解的相关性分数R k→ j Sub> l Sup>组合为相关性分数R j Sub> l Sup>用于下一步l− 1。
展开▼