Coursework for Deep Learning A-Z™: Hands-On Artificial Neural Networks
This is a practical course for implementing Deep Learning techniques through the use of Python based open-source libraries as TensorFLow, Theano, Keras and PyTorch. The course structure is divided in two parts, Supervised Neural Networks and Unsupervised. For each part a set of three study cases were provided to implement the theory from a single layer ANN up to Bolztmann Machines and Stacked Autoencoders. The following list describes the problems:
- Artificial Neural Networks to solve a Customer Churn problem
- Convolutional Neural Networks for Image Recognition
- Recurrent Neural Networks to predict Stock Prices
- Self-Organizing Maps to investigate Fraud
- Boltzmann Machines to create a Recomender System
- Stacked Autoencoders* to take on the challenge for the Netflix $1 Million prize