falconzyx · August 29, 2015 14:18 · Apr 3, 2015 · Apr 3, 2015 · Apr 2, 2015 · Apr 2, 2015
diff --git a/gistfile1.md b/gistfile1.md
@@ -44,7 +44,7 @@
   * [Recurrent Neural Networks for Collaborative Filtering](http://erikbern.com/?p=589)
 
 7. *Interesting courses* 
-  * [CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.github.io/) at Stanford by Andrej Karpathy
+  * [CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.stanford.edu/) at Stanford by Andrej Karpathy
   * [CS224d: Deep Learning for Natural Language Processing](http://cs224d.stanford.edu/) at Stanford by Richard Socher
   * [STA 4273H (Winter 2015): Large Scale Machine Learning](http://www.cs.toronto.edu/~rsalakhu/STA4273_2015/) at Toronto by Russ Salakhutdinov
   * [AM 207 Monte Carlo Methods, Stochastic Optimization](http://am207.org/) at Harvard by Verena Kaynig-Fittkau and Pavlos Protopapas 

diff --git a/gistfile1.md b/gistfile1.md
@@ -4,7 +4,7 @@
   * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng
   * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) Benjio & LeCun
 
-2. *Deep Neural Nets*
+2. *Deep Learning*
   * [Dropout: A Simple Way to Prevent Neural Networks from Overfitting](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf) by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov
   * [Understanding the difficulty of training deep feedforward neural networks](http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf) by Xavier Glorot and Yoshua Bengio
   * [On the difficulty of training Recurrent Neural Networks](http://arxiv.org/pdf/1211.5063v2.pdf) by Razvan Pascanu, Tomas Mikolov and Yoshua Bengio
@@ -16,6 +16,7 @@
   * [Efficient Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf) by LeCun, Bottou et al
   * [Towards Biologically Plausible Deep Learning](http://arxiv.org/abs/1502.04156) by Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Zhouhan Lin
   * [Training Recurrent Neural Networks](http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf) Phd thesis of Ilya Sutskever
+  * [A Probabilistic Theory of Deep Learning](http://arxiv.org/pdf/1504.00641v1.pdf) by Ankit B. Patel, Tan Nguyen, Richard G. Baraniuk
 
 3. *Scalable Machine Learning*
   * [Bring the Noise: Embracing Randomness is the Key to Scaling Up Machine Learning Algorithms](http://online.liebertpub.com/doi/pdf/10.1089/big.2013.0010) by Brian Delssandro

diff --git a/gistfile1.md b/gistfile1.md
@@ -48,3 +48,4 @@
   * [STA 4273H (Winter 2015): Large Scale Machine Learning](http://www.cs.toronto.edu/~rsalakhu/STA4273_2015/) at Toronto by Russ Salakhutdinov
   * [AM 207 Monte Carlo Methods, Stochastic Optimization](http://am207.org/) at Harvard by Verena Kaynig-Fittkau and Pavlos Protopapas 
   * [ACL 2012 + NAACL 2013 Tutorial: Deep Learning for NLP (without Magic)](http://www.socher.org/index.php/DeepLearningTutorial/DeepLearningTutorial) at NAACL 2013 by Richard Socher, Chris Manning and Yoshua Bengio
+  * [Video course on Deep Learning](https://www.youtube.com/playlist?list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH) by Hugo Larochelle
diff --git a/gistfile1.md b/gistfile1.md
@@ -47,3 +47,4 @@
   * [CS224d: Deep Learning for Natural Language Processing](http://cs224d.stanford.edu/) at Stanford by Richard Socher
   * [STA 4273H (Winter 2015): Large Scale Machine Learning](http://www.cs.toronto.edu/~rsalakhu/STA4273_2015/) at Toronto by Russ Salakhutdinov
   * [AM 207 Monte Carlo Methods, Stochastic Optimization](http://am207.org/) at Harvard by Verena Kaynig-Fittkau and Pavlos Protopapas 
+  * [ACL 2012 + NAACL 2013 Tutorial: Deep Learning for NLP (without Magic)](http://www.socher.org/index.php/DeepLearningTutorial/DeepLearningTutorial) at NAACL 2013 by Richard Socher, Chris Manning and Yoshua Bengio
diff --git a/gistfile1.md b/gistfile1.md
@@ -35,9 +35,15 @@
 
 6. *Interesting blog posts*
   * [Hacker's Guide to Neural Networks](https://karpathy.github.io/neuralnets/) by Andrej Karpathy
+  * [Breaking Linear Classifiers on ImageNet](http://karpathy.github.io/2015/03/30/breaking-convnets/) by Andrej Karpathy
   * [Classifying plankton with Deep Neural Networks](http://benanne.github.io/2015/03/17/plankton.html)
   * [Deep stuff about deep learning?](https://blogs.princeton.edu/imabandit/2015/03/20/deep-stuff-about-deep-learning/)
   * [Understanding Convolution in Deep Learning](https://timdettmers.wordpress.com/2015/03/26/convolution-deep-learning/)
   * [A Brief Overview of Deep Learning](http://yyue.blogspot.in/2015/01/a-brief-overview-of-deep-learning.html) by Ilya Sutskever
   * [Recurrent Neural Networks for Collaborative Filtering](http://erikbern.com/?p=589)
-
+
+7. *Interesting courses* 
+  * [CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.github.io/) at Stanford by Andrej Karpathy
+  * [CS224d: Deep Learning for Natural Language Processing](http://cs224d.stanford.edu/) at Stanford by Richard Socher
+  * [STA 4273H (Winter 2015): Large Scale Machine Learning](http://www.cs.toronto.edu/~rsalakhu/STA4273_2015/) at Toronto by Russ Salakhutdinov
+  * [AM 207 Monte Carlo Methods, Stochastic Optimization](http://am207.org/) at Harvard by Verena Kaynig-Fittkau and Pavlos Protopapas 
diff --git a/gistfile1.md b/gistfile1.md
@@ -32,7 +32,7 @@
 5. *Non Linear Units*
   * [Rectified Linear Units Improve Restricted Boltzmann Machines](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.165.6419&rep=rep1&type=pdf) by Nair & Hinton
   * [Mathematical Intuition for Performance of Rectified Linear Unit in Deep Neural Networks](https://www.academia.edu/7826776/Mathematical_Intuition_for_Performance_of_Rectified_Linear_Unit_in_Deep_Neural_Networks) by Alexandre Dalyec
-  * 
+
 6. *Interesting blog posts*
   * [Hacker's Guide to Neural Networks](https://karpathy.github.io/neuralnets/) by Andrej Karpathy
   * [Classifying plankton with Deep Neural Networks](http://benanne.github.io/2015/03/17/plankton.html)

diff --git a/gistfile1.md b/gistfile1.md
@@ -32,4 +32,12 @@
 5. *Non Linear Units*
   * [Rectified Linear Units Improve Restricted Boltzmann Machines](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.165.6419&rep=rep1&type=pdf) by Nair & Hinton
   * [Mathematical Intuition for Performance of Rectified Linear Unit in Deep Neural Networks](https://www.academia.edu/7826776/Mathematical_Intuition_for_Performance_of_Rectified_Linear_Unit_in_Deep_Neural_Networks) by Alexandre Dalyec
+  * 
+6. *Interesting blog posts*
+  * [Hacker's Guide to Neural Networks](https://karpathy.github.io/neuralnets/) by Andrej Karpathy
+  * [Classifying plankton with Deep Neural Networks](http://benanne.github.io/2015/03/17/plankton.html)
+  * [Deep stuff about deep learning?](https://blogs.princeton.edu/imabandit/2015/03/20/deep-stuff-about-deep-learning/)
+  * [Understanding Convolution in Deep Learning](https://timdettmers.wordpress.com/2015/03/26/convolution-deep-learning/)
+  * [A Brief Overview of Deep Learning](http://yyue.blogspot.in/2015/01/a-brief-overview-of-deep-learning.html) by Ilya Sutskever
+  * [Recurrent Neural Networks for Collaborative Filtering](http://erikbern.com/?p=589)
 
diff --git a/gistfile1.md b/gistfile1.md
@@ -23,6 +23,7 @@
   * [The TradeOffs of Large Scale Learning](http://papers.nips.cc/paper/3323-the-tradeoffs-of-large-scale-learning.pdf) by Leon Bottou & Olivier Bousquet
   * [Hash Kernels for Structured Data](http://www.jmlr.org/papers/volume10/shi09a/shi09a.pdf) by Qinfeng Shi et. al.
   * [Feature Hashing for Large Scale Multitask Learning](http://arxiv.org/pdf/0902.2206.pdf) by Weinberger et. al.
+  * [Large-Scale Learning with Less RAM via Randomization](http://www.eecs.tufts.edu/~dsculley/papers/round-model-icml.pdf) by a group of authors from Google
 
 4. *Gradient based Training*
   * [Practical Recommendations for Gradient-Based Training of Deep Architectures](http://arxiv.org/pdf/1206.5533v2.pdf) by Yoshua Bengio

diff --git a/gistfile1.md b/gistfile1.md
@@ -10,17 +10,25 @@
   * [On the difficulty of training Recurrent Neural Networks](http://arxiv.org/pdf/1211.5063v2.pdf) by Razvan Pascanu, Tomas Mikolov and Yoshua Bengio
   * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](http://arxiv.org/abs/1502.03167) by Sergey Ioffe and Christian Szegedy
   * [Deep Learning in Neural Networks: An Overview](http://arxiv.org/pdf/1404.7828v4.pdf) by Jurgen Schmidhuber
-  * [Stochastic Gradient Descent Tricks](http://research.microsoft.com/pubs/192769/tricks-2012.pdf) by L´eon Bottou
   * [Qualitatively characterizing neural network optimization problems](http://arxiv.org/abs/1412.6544) by Ian J. Goodfellow, Oriol Vinyals
   * [On Recurrent and Deep Neural Networks](http://www-etud.iro.umontreal.ca/~pascanur/papers/thesis.pdf) Phd thesis of Razvan Pascanu
   * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) by Yann LeCun and Yoshua Benjio
   * [Efficient Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf) by LeCun, Bottou et al
   * [Towards Biologically Plausible Deep Learning](http://arxiv.org/abs/1502.04156) by Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Zhouhan Lin
   * [Training Recurrent Neural Networks](http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf) Phd thesis of Ilya Sutskever
 
-2. *Scalable Machine Learning*
+3. *Scalable Machine Learning*
   * [Bring the Noise: Embracing Randomness is the Key to Scaling Up Machine Learning Algorithms](http://online.liebertpub.com/doi/pdf/10.1089/big.2013.0010) by Brian Delssandro
   * [Large Scale Machine Learning with Stochastic Gradient Descent](http://leon.bottou.org/publications/pdf/compstat-2010.pdf) by Leon Bottou
   * [The TradeOffs of Large Scale Learning](http://papers.nips.cc/paper/3323-the-tradeoffs-of-large-scale-learning.pdf) by Leon Bottou & Olivier Bousquet
   * [Hash Kernels for Structured Data](http://www.jmlr.org/papers/volume10/shi09a/shi09a.pdf) by Qinfeng Shi et. al.
   * [Feature Hashing for Large Scale Multitask Learning](http://arxiv.org/pdf/0902.2206.pdf) by Weinberger et. al.
+
+4. *Gradient based Training*
+  * [Practical Recommendations for Gradient-Based Training of Deep Architectures](http://arxiv.org/pdf/1206.5533v2.pdf) by Yoshua Bengio
+  * [Stochastic Gradient Descent Tricks](http://research.microsoft.com/pubs/192769/tricks-2012.pdf) by L´eon Bottou
+
+5. *Non Linear Units*
+  * [Rectified Linear Units Improve Restricted Boltzmann Machines](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.165.6419&rep=rep1&type=pdf) by Nair & Hinton
+  * [Mathematical Intuition for Performance of Rectified Linear Unit in Deep Neural Networks](https://www.academia.edu/7826776/Mathematical_Intuition_for_Performance_of_Rectified_Linear_Unit_in_Deep_Neural_Networks) by Alexandre Dalyec
+
diff --git a/gistfile1.md b/gistfile1.md
@@ -17,3 +17,10 @@
   * [Efficient Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf) by LeCun, Bottou et al
   * [Towards Biologically Plausible Deep Learning](http://arxiv.org/abs/1502.04156) by Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Zhouhan Lin
   * [Training Recurrent Neural Networks](http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf) Phd thesis of Ilya Sutskever
+
+2. *Scalable Machine Learning*
+  * [Bring the Noise: Embracing Randomness is the Key to Scaling Up Machine Learning Algorithms](http://online.liebertpub.com/doi/pdf/10.1089/big.2013.0010) by Brian Delssandro
+  * [Large Scale Machine Learning with Stochastic Gradient Descent](http://leon.bottou.org/publications/pdf/compstat-2010.pdf) by Leon Bottou
+  * [The TradeOffs of Large Scale Learning](http://papers.nips.cc/paper/3323-the-tradeoffs-of-large-scale-learning.pdf) by Leon Bottou & Olivier Bousquet
+  * [Hash Kernels for Structured Data](http://www.jmlr.org/papers/volume10/shi09a/shi09a.pdf) by Qinfeng Shi et. al.
+  * [Feature Hashing for Large Scale Multitask Learning](http://arxiv.org/pdf/0902.2206.pdf) by Weinberger et. al.
diff --git a/gistfile1.md b/gistfile1.md
@@ -16,3 +16,4 @@
   * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) by Yann LeCun and Yoshua Benjio
   * [Efficient Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf) by LeCun, Bottou et al
   * [Towards Biologically Plausible Deep Learning](http://arxiv.org/abs/1502.04156) by Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Zhouhan Lin
+  * [Training Recurrent Neural Networks](http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf) Phd thesis of Ilya Sutskever
diff --git a/gistfile1.md b/gistfile1.md
@@ -13,3 +13,6 @@
   * [Stochastic Gradient Descent Tricks](http://research.microsoft.com/pubs/192769/tricks-2012.pdf) by L´eon Bottou
   * [Qualitatively characterizing neural network optimization problems](http://arxiv.org/abs/1412.6544) by Ian J. Goodfellow, Oriol Vinyals
   * [On Recurrent and Deep Neural Networks](http://www-etud.iro.umontreal.ca/~pascanur/papers/thesis.pdf) Phd thesis of Razvan Pascanu
+  * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) by Yann LeCun and Yoshua Benjio
+  * [Efficient Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf) by LeCun, Bottou et al
+  * [Towards Biologically Plausible Deep Learning](http://arxiv.org/abs/1502.04156) by Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Zhouhan Lin
diff --git a/gistfile1.md b/gistfile1.md
@@ -12,3 +12,4 @@
   * [Deep Learning in Neural Networks: An Overview](http://arxiv.org/pdf/1404.7828v4.pdf) by Jurgen Schmidhuber
   * [Stochastic Gradient Descent Tricks](http://research.microsoft.com/pubs/192769/tricks-2012.pdf) by L´eon Bottou
   * [Qualitatively characterizing neural network optimization problems](http://arxiv.org/abs/1412.6544) by Ian J. Goodfellow, Oriol Vinyals
+  * [On Recurrent and Deep Neural Networks](http://www-etud.iro.umontreal.ca/~pascanur/papers/thesis.pdf) Phd thesis of Razvan Pascanu
diff --git a/gistfile1.md b/gistfile1.md
@@ -2,7 +2,7 @@
   * [Learning Feature Representations with K-means](http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf) by Adam Coates and Andrew Y. Ng 
   * [The devil is in the details: an evaluation of recent feature encoding methods](http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf) by Chatfield et. al. 
   * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng
-  * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) Bnejio & LeCun
+  * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) Benjio & LeCun
 
 2. *Deep Neural Nets*
   * [Dropout: A Simple Way to Prevent Neural Networks from Overfitting](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf) by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov

diff --git a/gistfile1.md b/gistfile1.md
@@ -2,6 +2,7 @@
   * [Learning Feature Representations with K-means](http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf) by Adam Coates and Andrew Y. Ng 
   * [The devil is in the details: an evaluation of recent feature encoding methods](http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf) by Chatfield et. al. 
   * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng
+  * [Scaling Learning Algorithms towards AI](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf) Bnejio & LeCun
 
 2. *Deep Neural Nets*
   * [Dropout: A Simple Way to Prevent Neural Networks from Overfitting](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf) by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov

diff --git a/gistfile1.md b/gistfile1.md
@@ -1,4 +1,13 @@
 1. *Feature Learning*
   * [Learning Feature Representations with K-means](http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf) by Adam Coates and Andrew Y. Ng 
   * [The devil is in the details: an evaluation of recent feature encoding methods](http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf) by Chatfield et. al. 
-  * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng 
+  * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng
+
+2. *Deep Neural Nets*
+  * [Dropout: A Simple Way to Prevent Neural Networks from Overfitting](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf) by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov
+  * [Understanding the difficulty of training deep feedforward neural networks](http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf) by Xavier Glorot and Yoshua Bengio
+  * [On the difficulty of training Recurrent Neural Networks](http://arxiv.org/pdf/1211.5063v2.pdf) by Razvan Pascanu, Tomas Mikolov and Yoshua Bengio
+  * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](http://arxiv.org/abs/1502.03167) by Sergey Ioffe and Christian Szegedy
+  * [Deep Learning in Neural Networks: An Overview](http://arxiv.org/pdf/1404.7828v4.pdf) by Jurgen Schmidhuber
+  * [Stochastic Gradient Descent Tricks](http://research.microsoft.com/pubs/192769/tricks-2012.pdf) by L´eon Bottou
+  * [Qualitatively characterizing neural network optimization problems](http://arxiv.org/abs/1412.6544) by Ian J. Goodfellow, Oriol Vinyals
diff --git a/gistfile1.md b/gistfile1.md
@@ -0,0 +1,4 @@
+1. *Feature Learning*
+  * [Learning Feature Representations with K-means](http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf) by Adam Coates and Andrew Y. Ng 
+  * [The devil is in the details: an evaluation of recent feature encoding methods](http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf) by Chatfield et. al. 
+  * [Emergence of Object-Selective Features in Unsupervised Feature Learning](http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf) by Coates, Ng 
diff --git a/gistfile1.txt b/gistfile1.txt
@@ -1,5 +0,0 @@
-Feature Learning
-
-1. Learning Feature Representations with K-means - Adam Coates and Andrew Y. Ng http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf
-2. The devil is in the details: an evaluation of recent feature encoding methods - Chatfield et. al. http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf
-3. Emergence of Object-Selective Features in Unsupervised Feature Learning - Coates, Ng http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf

diff --git a/gistfile1.txt b/gistfile1.txt
@@ -1,3 +1,5 @@
+Feature Learning
+
 1. Learning Feature Representations with K-means - Adam Coates and Andrew Y. Ng http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf
 2. The devil is in the details: an evaluation of recent feature encoding methods - Chatfield et. al. http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf
 3. Emergence of Object-Selective Features in Unsupervised Feature Learning - Coates, Ng http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf
diff --git a/gistfile1.txt b/gistfile1.txt
@@ -0,0 +1,3 @@
+1. Learning Feature Representations with K-means - Adam Coates and Andrew Y. Ng http://www.cs.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf
+2. The devil is in the details: an evaluation of recent feature encoding methods - Chatfield et. al. http://www.robots.ox.ac.uk/~vgg/publications/2011/Chatfield11/chatfield11.pdf
+3. Emergence of Object-Selective Features in Unsupervised Feature Learning - Coates, Ng http://web.stanford.edu/~acoates/papers/coateskarpathyng_nips2012.pdf
No results found