Filmed at PyData London 2017
Description In this tutorial we will learn Keras in ten steps (a.k.a. Jupyter Notebooks). We will warm up by learning how to create a multi layer network, and then we will go through more sophisticated topics such as implementing different types of networks (e.g. RNN, CNN), creating custom layers and discovering Keras internals. numpy proficiency and basic knowledge of Machine/Deep Learning are assumed.
Abstract Goal of the Tutorial
Introduce main features of Keras APIs to build Neural Networks. Learn how to implement simple and complex Deep Neural Networks Architectures using Keras. Discover Keras Implementation and Internals.
Note: examples and hands-on exercises will be provided along the way.
Outline (in ten Notebooks) Multi-layer Fully Connected Networks (and the backends) Bottleneck features and Embeddings Convolutional Networks Transfer Learning and Fine Tuning Residual Networks Recursive Neural Networks [Variational] AutoEncoders and Adversarials Multi-Modal Networks Custom Layers and Optimisers Interactive Networks and Callbacks Description Multi-layer Fully Connected Networks In this notebook we will learn the basic building blocks of Keras APIs to create deep neural networks. We will learn how to use the Sequential object as well as Functional and keras.backend APIs. First examples of MLP and Fully Connected Networks will be presented.