Introduction to Deep Learning using Python

Table of Content

1. Introduction
   1. Rosenblatt's Perceptron
   2. Limitations of Perceptrons
2. Multilayer Perceptrons
   1. Network Architecture
   2. Types of Hidden Units
3. How Neural Networks Learn
   1. Gradient-based Learning
   2. The Backpropagation Algorithmus
4. Deep Learning in Python
   1. Overview
   2. Tensorflow
   3. Keras
5. Regularization
   1. Weight Decay and other Parameter Penalties
   2. Early Stopping
   3. Dropout
   4. Batch Normalization
   5. Data Augmentation

References

• Haykin, Simon (2009) Neural Networks and Learning Machines. Pearson: New Jersey.
• Goodfellow, Ian et al. (2016) Deep Learning. The MIT Press: Cambridge, Massachusetts.
• Cristianini, Nello and John Shawe-Taylor (2000) An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press: Cambridge, UK.