Bibliography and Sources

1. Kriesel D. A Brief Introduction to Neural Netowrks. dkriesel.com; 2005.

2. Reid S. TuringFinance. [Online].; 2014 [cited 2016 Feb 20th. Available from: http://www.turingfinance.com/misconceptions-about-neural-networks/#brain.

3. DL4J. Restricted Boltzmann Machines. [Online].; 2016 [cited 2016 Feb 18. Available from: http://deeplearning4j.org/restrictedboltzmannmachine.html.

4. Hinton DGE. Scholarpedia. [Online].; 2007 [cited 2016 Feb 16. Available from: http://www.scholarpedia.org/article/Boltzmann_machine.

5. Weisstein EW. MathWorld--A Wolfram Web Resource. [Online].; 2016 [cited 2016 January 31. Available from: http://mathworld.wolfram.com/CompleteBipartiteGraph.html.

6. Hinton GE. Scholarpedia. [Online].; 2009 [cited 2016 Feb 5. Available from: http://www.scholarpedia.org/article/Deep_belief_nets.

7. DL4J. Deep-Belief Networks. [Online].; 2016 [cited 2016 January 31. Available from: http://deeplearning4j.org/deepbeliefnetwork.html.

8. deeplearning.net. Deep Learning. [Online]. [cited 2016 Feb 17th. Available from: http://deeplearning.net/tutorial/rbm.html.

9. Fischer A, Igel C. Training Restricted Boltzmann Machines: An Introduction. [Online]. [cited 2016 Feb 20th. Available from: http://image.diku.dk/igel/paper/TRBMAI.pdf.

10. Hinton G. CS Toronto | A Practical Guide to Training Restricted Boltzmann Machines. [Online].; 2010 [cited 2016 Feb 17th. Available from: https://www.cs.toronto.edu/~hinton/absps/guideTR.pdf.

11. iMonad. Restricted Boltzmann Machine - Short Tutorial. [Online]. [cited 2016 Feb 25th. Available from: http://imonad.com/rbm/restricted-boltzmann-machine/.

12. Hirokazu K, Norihiro T. TRAINING RESTRICTED BOLTZMANN MACHINES WITH AUXILIARY FUNCTION APPROACH. University of Tokyo, Graduate School of Information Science and Technology; 2014.

13. Bengio Y. Quora. [Online].; 2011 [cited 2016 Feb 17th. Available from: https://www.quora.com/What-is-contrastive-divergence.

14. University PS. Probability Theory and Mathematical Statistics | Penn State. [Online]. [cited 2016 Feb 28th. Available from: https://onlinecourses.science.psu.edu/stat414/node/191.

15. Woodford O. University of Oxford. [Online]. [cited 2016 Feb 15th. Available from: http://www.robots.ox.ac.uk/~ojw/files/NotesOnCD.pdf.

16. Carreira-Perpinan MA, Hinton GE. On Contrastive Divergence Learning. [Online]. [cited 2016 Feb 15th. Available from: http://www.gatsby.ucl.ac.uk/aistats/fullpapers/217.pdf.

17. University B. Gibbs Sampling. [Online]. [cited 2016 February 29th. Available from: http://cs.brown.edu/research/ai/dynamics/tutorial/Documents/GibbsSampling.html.

18. Philip, Resnik; Eric, Hardisty. [Online].; 2010 [cited 2016 Feb 20th. Available from: https://www.umiacs.umd.edu/~resnik/pubs/LAMP-TR-153.pdf.

19. Metacademy. [Online]. [cited 2016 Feb 21st. Available from: https://www.metacademy.org/graphs/concepts/gibbs_sampling.

20. Weisstein EW. Wolfram Alpha - Sigmoid Function. [Online]. [cited 2016 Feb 27th. Available from: http://mathworld.wolfram.com/SigmoidFunction.html.

21. deeplearning.net. deeplearning.net. [Online]. [cited 2016 March 1st. Available from: http://deeplearning.net/tutorial/DBN.html.

22. Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P. Why Does Unsupervised Pre-training Help Deep Learning? Montreal,Canada: Universite de Montreal, Departement d’informatique et de recherche op ´ erationnelle; 2010.

23. Lee H. NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning. [Online].; 2010 [cited 2016 Feb 28th. Available from: https://deeplearningworkshopnips2010.files.wordpress.com/2010/09/nips10-workshop-tutorial-final.pdf.

24. Bengio Y, Lamblin P. Deep Learning Workshop. [Online].; 2010 [cited 2016 March 1st. Available from: https://deeplearningworkshopnips2010.files.wordpress.com/2010/11/nips_deep_workshop_2010.pdf.

25. Bengio Y, Lamblin P, Popovici D, Larochelle H. Carnegie Melon University Computer Science. [Online].; 2007 [cited 2016 March 2nd. Available from: http://deeplearning.cs.cmu.edu/notes/hefny_Greedy.pdf.

26. MedCalc. MedCalc. [Online]. [cited 2016 Feb 19th. Available from: https://www.medcalc.org/manual/logistic_regression.php.

27. Hosmer DW, Lemeshow S. Applied Logistic Regression (2nd ed.). , Computer Science; 2000. Report No.: ISBN 0-471-35632-8.

28. Green WH. Econometric Analysis (Seventh ed.). ; 2012. Report No.: ISBN 978-0-273-75356-8.

29. UFLDL S. Stanford.edu. [Online]. [cited 2016 March 1. Available from: http://ufldl.stanford.edu/tutorial/supervised/SoftmaxRegression/.

30. deeplearning.net. deeplearning.net. [Online]. [cited 2016 February 12th. Available from: http://deeplearning.net/tutorial/logreg.html.

31. THE MNIST DATABASE. [Online]. [cited 2016 Feb 27th. Available from: http://yann.lecun.com/exdb/mnist/.

32. Vivin. Github | DigitRecognizingNeuralNetwork. [Online].; 2011 [cited 2016 Feb 28th. Available from: (3) https://github.com/vivin/DigitRecognizingNeuralNetwork/blob/master/src/main/java/net/vivin/service/DigitImageLoadingService.java.

33. Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Toronto; Singapore: University of Toronto; National University of Singapore, Department of Computer Science.

34. Vasilev I. Toptotal. [Online]. [cited 2016 March 1st. Available from: https://www.toptal.com/machine-learning/an-introduction-to-deep-learning-from-perceptrons-to-deep-networks.

35. Stergiou C, Siganos D. NEURAL NETWORKS. [Online]. [cited 2016 Feb 13th. Available from: https://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html#Introduction to neural networks.

36. Bengio Y, LeCun Y. University of Toronto Computer Science. [Online].; 2009 [cited 2016 March 1st. Available from: http://www.cs.toronto.edu/~rsalakhu/deeplearning/yoshua_icml2009.pdf.



Images

1. Image modified from: https://upload.wikimedia.org/wikipedia/commons/8/8b/Neural_network_bottleneck_achitecture.svg, Accesed on 20th Feb 2016.

2. Image taken from: http://static.vecteezy.com/system/resources/previews/000/053/107/non_2x/brain-vector.jpg, Accesed on 20th Feb 2016. 3. Image has been adapted from http://mechanicalforex.com/wp-content/uploads/2011/06/NN.png, Accessed 28th Feb 2016

4.Image adapted from https://stackoverflow.com/questions/13235972/bipartite-network-graph-with-ggplot2, Accessed on 20th Feb 2016.

5. Image adapted from http://images.cnitblog.com/blog/326731/201308/18151139-9bff6318a201473e8a79173d1b578671.png, Accessed on 29th Feb 2016.

6. Image adapted from http://deeplearning4j.org/restrictedboltzmannmachine.html#define, Accessed on 20th Feb 2016.

7.Image adapted from http://sebastianruder.com/optimizing-gradient-descent/, Accessed on 28th Feb 2016.

8. Image adapted from http://recognize-speech.com/acoustic-model/knn/training-neural-networks, Accessed on 29th Feb 2016

9. Image adapted from https://www.werc.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/2014-10-14_LKE_Tutorial_on_Deep_Learning.pdf, Accessed on 3rd March.

10. Image Adapted from https://www.metacademy.org/roadmaps/rgrosse/deep_learning, Accessed on 3rd Msrch 2016.

11. Image adapted from https://assets.toptal.io/uploads/blog/image/335/toptal-blog-image-1395721542588.png, Accessed on 1st March 2016

12. Image taken from http://image.diku.dk/igel/paper/TRBMAI.pdf, Accessed on 27th February 2016



Other Technical Sources

With regards to web deisgn and our implementation

1. Foundation, the CSS framework used for this website http://foundation.zurb.com/

2. Google Fonts - Where we got several free fonts. https://www.google.com/fonts# 2. Google Fonts - Where we got several free fonts. https://www.google.com/fonts#

3. Animate.css - Where we got certain animations for the webpage. https://github.com/daneden/animate.css

4. Code-prettify - A template for making code readable on https://github.com/google/code-prettify

5. Smooth Scrolling http://www.dwuser.com/education/content/quick-guide-adding-smooth-scrolling-to-your-webpages/

6. Desert.css, the specific code prettify template we used https://cdn.rawgit.com/google/code-prettify/master/styles/desert.css

7. Mathjax - for our math functions - https://www.mathjax.org/

8. Modernizr - https://modernizr.com/

9. Heroku hosting - https://www.heroku.com/

10. Ginrou on github - https://github.com/ginrou/handwritten_classifier