======CS551: Introduction to Deep Learning======
This course will provide basic understanding of deep learning and how to solve classification problems having large amount of data. In this course several open source tools will be demonstrated to build deep learning network.

=====Class timings=====
  * Tuesday - 0900-1000
  * Wednesday - 0900-1000
  * Friday  - 1500-1600

=====Syllabus=====
Brief introduction of big data problem. Overview of linear algebra, probability, numerical computation. Basics of Machine learning/Feature engineering. Neural network. Tutorial for Tools. Deep learning network - Shallow vs Deep network, Deep feedforward network, Gradient based learning - Cost function, soft max, sigmoid function, Hidden unit - ReLU, Logistic sigmoid, hyperbolic tangent Architecture design, SGD, Unsupervised learning - Deep Belief Network, Deep Boltzmann Machine, Factor analysis, Autoencoders. Regularization. Optimization for training deep model. Advanced topics - Convolutional Neural Network, Recurrent Neural Network/ Sequence modeling, LSTM, Reinforcement learning. Practical applications  – Vision, speech, NLP, etc. 

=====Books=====
  * Ian Goodfellow, Yoshua Bengio and Aaron Courville, “Deep Learning”, Book in preparation for MIT Press, 2016. (available online) 
  * Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie, “The elements of statistical learning”, Springer Series in Statistics, 2009.

=====Slides=====
  * {{ :courses:2017:01_intro_to_dl.pdf |Introduction to Deep Learning}}
  * {{ :courses:2017:02_linear_algebra.pdf |Overview of linear algebra and probability}}
  * {{ :courses:2017:03_feature_engg.pdf |Overview of feature engineering}}
  * {{ :courses:2017:04_neural_network.pdf |Neural Network}}
  * {{ :courses:2017:keras.pdf | Demonstration of Keras}} - [[:courses:2017:Installation guide|Installation guide]], [[:courses:2017:Sample code|Sample code]] (Presented by Niraj Kumar) 
  * {{ :courses:2017:05_dl_network.pdf |Deep Feedforward Network}}
  * {{ :courses:2017:06_regularization.pdf |Regularization}}
  * {{ :courses:2017:07_optimization.pdf | Optimization of Neural Network}}
  * {{ :courses:2017:08_cnn.pdf | Convolutional Neural Network}}
  * {{ :courses:2017:09_rnn.pdf | Recurrent Neural Network}}
  * {{ :courses:2017:10_practical_methods.pdf | Practical methodology}}
  * {{ :courses:2017:11_drl.pdf | Deep Reinforcement Learning}}
=====Additional Reading Materials=====
  * {{ :courses:2017:matrixcalculus.pdf|Matrix differentiation}} by Randal J. Barnes, Department of Civil Engineering, University of Minnesota, Minneapolis, Minnesota, USA
  * [[http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html|Deep Learning, Nature]]
  * [[http://ieeexplore.ieee.org/abstract/document/485891/ | Artificial Neural Networks: A tutorial]]
  * [[http://www.asimovinstitute.org/neural-network-zoo/|The neural network zoo]]
  * [[https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ | A Step by Step Backpropagation Example]]
  * [[http://www.jefkine.com/general/2016/09/05/backpropagation-in-convolutional-neural-networks/|Backpropagation in convolutional neural network]]
  * [[http://karpathy.github.io/2015/05/21/rnn-effectiveness/ | Andrej Karpathy blog]]
  * [[https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/ | Blog on LSTM-RNN]]


=====Information related to projects=====
  * {{ :courses:2017:projectlist.pdf |Data resources}}
  * [[ :courses:2017:generalinformation| General information]]
  * {{ :courses:2017:cs551_project_ideas_v01.pdf |List of projects}} - These are the projects received so far.
  * [[ :courses:2017:Final_Project_Report | Final project report]]