Paper之DL之BP：《Understanding the difficulty of training deep feedforward neural networks》

?

?

目錄

原文解讀

文章內容以及劃重點

結論

---

?

?

?

原文解讀

原文：Understanding the difficulty of training deep feedforward neural networks

?

文章內容以及劃重點

Sigmoid的四層局限

sigmoid函數的test loss和training loss要經過很多輪數一直為0.5，后再有到0.1的差強人意的變化。

?

? ? ?We hypothesize that this behavior is due to the combinationof random initialization and the fact that an hidden unitoutput of 0 corresponds to a saturated sigmoid. Note that deep networks with sigmoids but initialized from unsupervisedpre-training (e.g. from RBMs) do not suffer fromthis saturation behavior.

?

tanh、softsign的五層局限

換為tanh函數，就會很好很快的收斂

?

結論

1、The normalization factor may therefore be important when initializing deep networks because of the multiplicative effect through layers, and we suggest the following initialization procedure to approximately satisfy our objectives of maintaining activation variances and back-propagated gradients variance as one moves up or down the network. We call it the normalized initialization

2、結果可知分布更加均勻

? ? ?Activation values normalized histograms with ?hyperbolic tangent activation, with standard (top) vs normalized ?initialization (bottom). Top: 0-peak increases for ?higher layers.
? ? ? ?Several conclusions can be drawn from these error curves: ?
(1)、The more classical neural networks with sigmoid or ?hyperbolic tangent units and standard initialization ?fare rather poorly, converging more slowly and apparently ?towards ultimately poorer local minima.?
(2)、The softsign networks seem to be more robust to the ?initialization procedure than the tanh networks, presumably ?because of their gentler non-linearity.?
(3)、For tanh networks, the proposed normalized initialization ?can be quite helpful, presumably because the ?layer-to-layer transformations maintain magnitudes of activations (flowing upward) and gradients (flowing backward).
3、Sigmoid 5代表有5層，N代表正則化，可得出預訓練會得到更小的誤差

相關文章
Understanding the difficulty of training deep feedforward neural networks 本文作者為：Xavier Glorot與Yoshua Bengio。

總結

以上是生活随笔為你收集整理的Paper之DL之BP：《Understanding the difficulty of training deep feedforward neural networks》的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。