ResearchLinks.txt

##########################################################################################
This file contains all the research links and blogs for the topics which will help in better understanding of the problem.For video tutorials use Coursera, Udemy or Pluralsight
##########################################################################################

—> Recommendation theory and basics

https://www.analyticsvidhya.com/blog/2015/10/recommendation-engines/
https://www.coursera.org/learn/machine-learning/home/week/9

—> Nearest neighbour model

http://rnowling.github.io/data/science/2016/10/29/knn-recsys.html
http://cs229.stanford.edu/proj2008/Wen-RecommendationSystemBasedOnCollaborativeFiltering.pdf

—> Latent factor model Code & PPT(Already uploaded on confluence Page)

https://github.com/katbailey/factorizer/blob/master/factorizer.py
http://katbailey.github.io/post/matrix-factorization-with-tensorflow/
https://github.com/shashankg7/Matrix-Factorization-GPU ##(See this)

—> Netflix challenge for recommendations

http://blog.echen.me/2011/10/24/winning-the-netflix-prize-a-summary/


	######## In depth knowledge of neural networks required further #######
Prerequisite: There are a lot of tutorials and videos on neural networks available online (Udemy , Coursera and blogs).
So neural network working should be clear before proceeding further. 

—> Help on neural networks

http://neuralnetworksanddeeplearning.com/
https://deeplearning4j.org
https://github.com/shashankg7


—> Importance of activation functions in NN

https://www.quora.com/What-is-the-role-of-the-activation-function-in-a-neural-network
http://playground.tensorflow.org/

—> Collaborative CNNs for Spotify and Youtube

http://benanne.github.io/2014/08/05/spotify-cnns.html
https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/45530.pdf


—> Research paper & blog for RBM intro

https://deeplearning4j.org/restrictedboltzmannmachine
http://www.cs.toronto.edu/~rsalakhu/papers/rbmcf.pdf


—> Research for RBM implementation

http://image.diku.dk/igel/paper/AItRBM-proof.pdf


—> Help for autoencoders intro

https://deeplearning4j.org/deepautoencoder
https://pgaleone.eu/neural-networks/2016/11/18/introduction-to-autoencoders/
https://walmart.udemy.com/deeplearning/learn/v4/t/lecture/6866168?start=0

—> Help for autoencoders implementation

https://blog.keras.io/building-autoencoders-in-keras.html

—> Reference code for diff models for recommendation

https://github.com/saurabhmathur96/movie-recommendations


—> Further research with RNNs (For curiosity)

https://arxiv.org/pdf/1606.07792.pdf
https://arxiv.org/pdf/1511.06939.pdf
https://cs224d.stanford.edu/reports/LiuSingh.pdf (Handling Sparsity in the UI matrix-Good)