深度神經(jīng)網(wǎng)絡(luò)可解釋性方法匯總，附Tensorflow代碼實現(xiàn)
理解神經(jīng)網(wǎng)絡(luò)：人們一直覺得深度學(xué)習(xí)可解釋性較弱。然而，理解神經(jīng)網(wǎng)絡(luò)的研究一直也沒有停止過，本文就來介紹幾種神經(jīng)網(wǎng)絡(luò)的可解釋性方法，并配有能夠在Jupyter下運行的代碼連接。
Activation Maximization
通過激活最化來解釋深度神經(jīng)網(wǎng)絡(luò)的方法一共有兩種，具體如下：
1.1 Activation Maximization (AM)
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/1.1%20Activation%20Maximization.ipynb
1.2 Performing AM in Code Space
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/1.3%20Performing%20AM%20in%20Code%20Space.ipynb
Layer-wise Relevance Propagation
層方向的關(guān)聯(lián)傳播，一共有5種可解釋方法。Sensitivity Analysis、Simple Taylor Decomposition、Layer-wise Relevance Propagation、Deep Taylor Decomposition、DeepLIFT。它們的處理方法是：先通過敏感性分析引入關(guān)聯(lián)分?jǐn)?shù)的概念，利用簡單的Taylor Decomposition探索基本的關(guān)聯(lián)分解，進而建立各種分層的關(guān)聯(lián)傳播方法。具體如下：
2.1 Sensitivity Analysis
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.1%20Sensitivity%20Analysis.ipynb
2.2 Simple Taylor Decomposition
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.2%20Simple%20Taylor%20Decomposition.ipynb
2.3 Layer-wise Relevance Propagation
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.3%20Layer-wise%20Relevance%20Propagation%20%281%29.ipynb
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.3%20Layer-wise%20Relevance%20Propagation%20%282%29.ipynb
2.4 Deep Taylor Decomposition
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.4%20Deep%20Taylor%20Decomposition%20%281%29.ipynb
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.4%20Deep%20Taylor%20Decomposition%20%282%29.ipynb
2.5 DeepLIFT
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/2.5%20DeepLIFT.ipynb
Gradient Based Methods
基于梯度的方法有：反卷積、反向傳播， 引導(dǎo)反向傳播，積分梯度和平滑梯度這幾種。具體可以參考如下鏈接：
https://github.com/1202kbs/Understanding-NN/blob/master/models/grad.py
詳細(xì)信息如下：
3.1 Deconvolution
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/3.1%20Deconvolution.ipynb
3.2 Backpropagation
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/3.2%20Backpropagation.ipynb
3.3 Guided Backpropagation
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/3.3%20Guided%20Backpropagation.ipynb
3.4 Integrated Gradients
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/3.4%20Integrated%20Gradients.ipynb
3.5 SmoothGrad
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/3.5%20SmoothGrad.ipynb
Class Activation Map
類激活映射的方法有3種，分別為：Class Activation Map、Grad-CAM、 Grad-CAM++。在MNIST上的代碼可以參考：
https://github.com/deepmind/mnist-cluttered
每種方法的詳細(xì)信息如下：
4.1 Class Activation Map
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/4.1%20CAM.ipynb
4.2 Grad-CAM
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/4.2%20Grad-CAM.ipynb
4.3 Grad-CAM++
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/4.3%20Grad-CAM-PP.ipynb
Quantifying Explanation Quality
雖然每一種解釋技術(shù)都基于其自身的直覺或數(shù)學(xué)原理，但在更抽象的層次上確定好解釋的特征并能夠定量地測試這些特征也很重要。這里再推薦兩種基于質(zhì)量和評價的可解釋性方法。具體如下：
5.1 Explanation Continuity
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/5.1%20Explanation%20Continuity.ipynb
5.2 Explanation Selectivity
相關(guān)代碼如下：
http://nbviewer.jupyter.org/github/1202kbs/Understanding-NN/blob/master/5.2%20Explanation%20Selectivity.ipynb
