The purpose of this project is to learn how to build neural and convolutional networks using libraries like

1. Tensorflow: https://www.tensorflow.org/
2. scikit-learn: https://scikit-learn.org/stable/index.html
3. Keras: https://keras.io/

The project is following along Deep Learning A-Z 2024: Neural Networks, AI & ChatGPT: https://www.udemy.com/course/deeplearning/

The parts of the project consist of:

Part 1: Artificial Neural Networks

Readings: A Neural Network in 13 lines of Python: https://iamtrask.github.io/2015/07/27/python-network-part2/ How Backpropagation algorithms work: http://neuralnetworksanddeeplearning.com/chap2.html

Part 2: Convolutional Neural Networks

Readings: Introduction to Convolutional Neural Networks: https://cs.nju.edu.cn/wujx/paper/CNN.pdf Understanding Convolutional Neural Networks with A Mathamatical Model: https://arxiv.org/pdf/1609.04112 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification: https://arxiv.org/pdf/1502.01852 Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition: https://ais.uni-bonn.de/papers/icann2010_maxpool.pdf ** 9 Deep Learning Papers You Need To Know: https://adeshpande3.github.io/ A friendly introduction to cross-entropy loss: https://rdipietro.github.io/friendly-intro-to-cross-entropy-loss/ Softmax Classification with Cross Entropy: https://peterroelants.github.io/posts/cross-entropy-softmax/

Part 3: Recurrent Neural Networks

Readings: The Unreasonable Effectivness of Recurrent Neural Networks: https://karpathy.github.io/2015/05/21/rnn-effectiveness/ Visualizing and Understanding Recurrent Networks: https://arxiv.org/pdf/1506.02078 LSTM: A Search Space Odyssey: https://arxiv.org/pdf/1503.04069

Part 4: Self Organizing Maps

Readings: Kohonen's Self Organizing Feature Maps: http://www.ai-junkie.com/ann/som/som1.html

Part 5: Boltzmann Machines

Readings: Machine Learning Research Group: https://www.robots.ox.ac.uk/~parg/ University of Toronto Department of Statistical Sciences: https://www.statistics.utoronto.ca/

Part 6: AutoEncoders

Readings: Building Autoencoders in Keras: https://blog.keras.io/building-autoencoders-in-keras.html Deep learning, sparse autoencoders: https://mccormickml.com/ k-Sparse Autoencoders: https://arxiv.org/pdf/1312.5663 Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Netowrk with a Local Denoising Criterion

Data sets come from https://www.superdatascience.com/deep-learning