前向人工神經(jīng)網(wǎng)絡敏感性研究(編輯修改稿)
2025-02-02 00:40 本頁面
【文章內容簡介】 yRWX nn18 I n p u t X1 L a y e r 1 … . . . L a y e r ( L 1 ) L a y e r L Ou tp u t YL ? ? 2n 2?Ln ? ? 11x ? ? ? ? 2n 2?Ln ? ? ? Ly1 12x? ? 110?nx? ? 10nx? ? ? ? 2n 2?Ln ? ? ? LnLy ? ? 2n 2?Ln ? ? 0ni n p u ts 1n n e u r o n s 1?Lnn e u r o n s Lnn e u r o n s19 WW ?? X F N N YY ?? 20 W XX ?? F N N YY ?? 21 ? Effects of input amp。 weight deviations on neurons’ sensitivity ? Sensitivity increases with input and weigh deviations, but the increase has an upper bound. 22 ? Effects of input dimension on neurons’ sensitivity There exists an optimal value for the dimension of input, which yields the highest sensitivity value. 23 ? Effects of input amp。 weight deviations on MLPs’ sensitivity Sensitivity of an MLP increases with the input and weight deviations. 24 ? Effects of the number of neurons in a layer – Sensitivity of MLPs: { n221 | 1?n ?10 } to the dimension of input. 25 – Sensitivity of MLPs: { 2n21 | 1?n ?10 } to the number of neurons in the 1st layer. 26 – Sensitivity of MLPs: { 22n1 | 1?n ?10 } to the number of neurons in the 2nd layer . There exists an optimal value for the number of neurons in a layer, which yields the highest sensitivity value. The nearer a layer to the output layer is, The more effect the number of neurons in the layer has. 27 ? Effects of the number of layers – Sensitivity of MLPs:{21,221,..,22222222221} to the n
教學課件相關推薦
鄂ICP備17016276號-1