最近在學習deeplearning的時候接觸到了bottle-neck layer，好奇它的作用於是便扒了一些論文（論文鏈接放在文末吧），系統的了解一下bottle-neck feature究竟有什么用。
論文[1]中對bottle-neck feature的介紹：
對應的圖示如下：
直觀的理解是這玩意兒應該是用來降維用的，沒錯，那為什么用它比較好呢，另一篇論文[2]給了解釋：
If we do not want to use the dimensionality reduction techniques, and want to obtain the features suitable for the classification as outcome of neural net training process, a bottle-neck has to be created in the neural net structure. The neural net has the ability of nonlinear compression of the input features and of classification of such compressed features. If the trained neural net with bottle-neck has a good classification accuracy, we know that the bottle-neck outputs represents the underlying speech well.（感興趣的可以看看論文的背景，這樣比較好理解）
個人認為非線性的壓縮能力以及在網絡中的可學習性是這個idea突出的地方（感覺過幾個月回頭看會覺得這個觀點很好笑哈哈 姑且先寫在這里吧）
reference:
[1] Efficient Processing of Deep Neural Networks: A Tutorial and Survey Vivienne Sze, Senior Member, IEEE, Yu-Hsin Chen, Student Member, IEEE, Tien-Ju Yang, Student Member, IEEE, Joel Emer, Fellow, IEEE
[2] PROBABILISTIC AND BOTTLE-NECK FEATURES FOR LVCSR OF MEETINGS Frantisek ˇ Grezl, ´ Martin Karafiat, ´ Stanislav Kontar´ and Jan Cernoc ˇ ky´ Speech@FIT group, Brno University of Technology, Czech Republic
鏈接：http://www.fit.vutbr.cz/research/groups/speech/publi/2007/grezl_BN_fea_icassp_2007.pdf
https://arxiv.org/pdf/1703.09039.pdf （要梯子）