Aggregators

• Short Science - (summaries) http://www.shortscience.org/venue?key=conf/nips
• VK - Deep Learning community (Papers, codes, articles) https://vk.com/deeplearning
• Arix-Sanity - better arxiv search http://www.arxiv-sanity.com/
• GitXiv (Arxiv and Git code) http://gitxiv.com/
• Arxiv-Vanity - HTML rendeing of Arxiv pages https://www.arxiv-vanity.com/

General

• CS: What Papers everyone should read http://cstheory.stackexchange.com/questions/1168/what-papers-should-everyone-read
• MATH: A single paper everyone should read http://mathoverflow.net/questions/2144/a-single-paper-everyone-should-read
• How to read a paper - Keshava http://blizzard.cs.uwaterloo.ca/keshav/home/Papers/data/07/paper-reading.pdf
• How to write a proof - Leslie Lamport http://research.microsoft.com/en-us/um/people/lamport/pubs/lamport-how-to-write.pdf
• How to write papers Oded Goldreich http://www.wisdom.weizmann.ac.il/~oded/PS/re-writing.pdf
• How not to write papers Oded Goldreich http://www.cs.iastate.edu/~honavar/write-not.pdf

Big Data

• The PageRank Citation Ranking: Bringing Order to the Web
• MapReduce: Simplified Data Processing on Large Clusters
• The Google File System
• Amazon’s Dynamo
• Bigtable: A Distributed Storage System for Structured Data
• A Few Useful Things to Know about Machine Learning
• Random Forests
• A Relational Model of Data for Large Shared Data Banks
• Map-Reduce for Machine Learning on Multicore
• Pasting Small Votes for Classification in Large Databases and On-Line
• Recommendations Item-to-Item Collaborative Filtering
• Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
• Spanner: Google’s Globally-Distributed Database
• Megastore: Providing Scalable, Highly Available Storage for Interactive Services
• F1: A Distributed SQL Database That Scales
• APACHE DRILL: Interactive Ad-Hoc Analysis at Scale
• A New Approach to Linear Filtering and Prediction Problems
• Top 10 algorithms on Data mining
• Resilient Distributed Data - SPARK

Computer Vision

• Building High-level Features Using Large Scale Unsupervised Learning
• Distinctive image features from scale-invariant keypoints
• A theory for multiresolution signal decomposition: The wavelet representation
• A computational approach to edge detection
• Snakes: Active contour models
• Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images
• Eigenfaces for Recognition
• Determining optical flow
• Scale-space and edge detection using anisotropic diffusion
• Rapid object detection using a boosted cascade of simple features
• An iterative image registration technique with an application to stereo vision
• Normalized cuts and image segmentation
• Histograms of oriented gradients for human detection
• Mean shift: A robust approach toward feature space analysis
• The Laplacian pyramid as a compact image code
• Condensation—conditional density propagation for visual tracking
• Good features to track
• A model of saliency-based visual attention for rapid scene analysis
• A performance evaluation of local descriptors
• Fast approximate energy minimization via graph cuts
• Surf: Speeded up robust features
• Neural network-based face detection
• Emergence of simple-cell receptive field properties by learning a sparse code for natural images
• Shape matching and object recognition using shape contexts
• Shape modeling with front propagation: A level set approach
• The structure of images
• Shape and motion from image streams under orthography: a factorization method
• Active appearance models
• Scale & affine invariant interest point detectors
• Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach
• Feature extraction from faces using deformable templates
• Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation
• Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories
• Face detection in color images
• Efficient graph-based image segmentation
• Visual categorization with bags of keypoints
• Object class recognition by unsupervised scale-invariant learning
• Recovering high dynamic range radiance maps from photographs
• A comparison of affine region detectors
• A bayesian hierarchical model for learning natural scene categories

Machine Learning

• Breiman, L. 2001. “Statistical Modeling: The Two Cultures (with Comments and a Rejoinder by the Author).” Statistical Science 16:199–231.

Supervised Learning

• Regression: Panik, M. J. 2009. Regression Modeling: Methods, Theory, and Computation with SAS. Boca Raton, FL: CRC Press. (Disclosure: my favorite regression book.)
• Decision tree: Breiman, L., Friedman, J., Olshen, R., and Stone, C. 1984. Classification and Regression Trees. Belmont, CA: Wadsworth.
• Random forest: Breiman, L. 2001. “Random Forests.” Machine Learning 45:5–32.
• Gradient boosting: Friedman, J. H. 2001. “Greedy Function Approximation: A Gradient Boosting Machine.” Annals of Statistics 29:1189–1232.
• Neural network: Rumelhart, D. E., Hinton, G. E., and Williams, R. J. 1986. “Learning Representations by Back-Propagating Errors.” Nature 323:533–536.
• Support vector machine: Cortes, C. and Vapnik, V. 1995. “Support-Vector Networks.” Machine Learning 20:273–297.
• Naïve Bayes: Friedman, N., Geiger, D., and Goldszmidt, M. 1997. “Bayesian Network Classifiers.” Machine Learning 29:131–163.
• Neighbors: Cover, T. and Hart, P. 1967. “Nearest Neighbor Pattern Classification.” IEEE Transactions on Information Theory 13:21–27.
• Gaussian processes: Seeger, M. 2004. “Gaussian Processes for Machine Learning.” International Journal of Neural Systems 14:69–106.

Unsupervised Learning

• A priori rules: Agrawal, R., Imieliński, T., and Swami, A. 1993. “Mining Association Rules between Sets of Items in Large Databases.” ACM SIGMOD Record 22:207–216.
• k-means clustering: Hartigan, J. A. and Wong, M. A. 1979. “Algorithm AS 136: A k-Means Clustering Algorithm.” Journal of the Royal Statistical Society, Series C 28:100–108.
• Mean shift clustering: Cheng, Y. 1995. “Mean Shift, Mode Seeking, and Clustering.” IEEE Transactions on Pattern Analysis and Machine Intelligence 17:790–799.
• Spectral clustering: Von Luxburg, U. 2007. “A Tutorial on Spectral Clustering.” Statistics and Computing 17:395–416.
• Kernel density estimation: Silverman, B. W. 1986. Density Estimation for Statistics and Data Analysis. Vol. 26. Boca Raton, FL: CRC Press.
• Non-negative matrix factorization: Lee, D. D. and Seung, H. S. 1999. “Learning the Parts of Objects by Non-negative Matrix Factorization.” Nature 401:788–791.
• Kernel PCA: Schölkopf, B., Smola, A., and Müller, K.-R. 1997. “Kernel Principal Component Analysis.” In Artificial Neural Networks—ICANN’97, 583–588. Berlin: Springer.
• Sparse PCA: Zou, H., Hastie, T., and Tibshirani, R. 2006. “Sparse Principal Component Analysis.” Journal of Computational and Graphical Statistics 15:265–286.
• Singular value decomposition: Golub, G. H. and Reinsch, C. 1970. “Singular Value Decomposition and Least Squares Solutions.” Numerische Mathematik 14:403–420.

Semi-Supervised Learning

• Denoising autoencoders: Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. 2008. “Extracting and Composing Robust Features with Denoising Autoencoders.” Proceedings of the 25th International Conference on Machine Learning. New York: ACM.
• Expectation maximization: Nigam, K., McCallum, A.K., Thrun, S. and Mitchell, T. 2000. “Text Classification from Labeled and Unlabeled Documents using EM.” Machine Learning 39:103-134.
• Manifold regularization: Belkin, M., Niyogi, P., and Sindhwani, V. 2006. “Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples.” The Journal of Machine Learning Research 7:2399-2434.
• Transductive support vector machines: Joachims, T. 1999. “Transductive Inference for Text Classification Using Support Vector Machines.” Proceedings of the 16th International Conference on Machine Learning. New York: ACM. (source (for ML) : http://qr.ae/LPuHs )

Other applications

• Character Recognition (SOTA): Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks