Deep Neural Networks I

Repository of Deep Neural Network I classes taught by Prof. Dr Jorge Leonid Aching Samatelo - Ufes, 2018/1

Summary

1. Introduction
2. Review of Linear Algebra
3. Fundamentals of Mathematical Optimization
   • Gradient Descent (GD)
   • Gradient Descent Stochastic (GDS)
4. Linear Regression
   • Regression and Regularization
5. Linear Binary Classification
   • Perceptron and logistic regression
6. Multi-class Classification
   • Softmax Classifier
   • Multilayer Neural Network
     • Backpropagation Learning Algorithm
7. Convolutional Neural Networks (CNN)
   • Concepts and classic architectures
8. Regularization
   • Concepts and Techniques of Regularization
9. Transfer Learning

Tools:

• Google Colaboratory
• Docker

Docker

$ nvidia-docker container run --rm -ti -p 8888:8888 -p 6006:6006 --memory=12g -v /directory/:/src -v /directory/:/data hsneto/jupyter:keras-gpu-1.1

Bibliography

• Ian Goodfellow, Yoshua Bengio e Aaron Courville, "Deep Learning ", MIT Press, 2016.
• Simon O. Haykin, "Neural Networks and Learning Machines", Pearson Education, 2009
• Jordi Torres, “FIRST CONTACT WITH TENSORFLOW”, Barcelona, 2016.