O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Advanced Deep Learning with Keras

Video Description

Explore Deep Learning with Keras

About This Video

  • Recognize whose practical applications can benefit from Deep Learning
  • Get equipped with the knowledge of building, training and using convolutional neural network
  • Solve supervised and unsupervised learning problems using images, text and time series

In Detail

Keras is an open source neural network library written in Python. It is capable of running on top of MXNet, Deeplearning4j, Tensorflow, CNTK, or Theano. Designed to enable fast experimentation with deep neural networks, it focuses on being minimal, modular, and extensible.

This course provides a comprehensive introduction to deep learning. We start by presenting some famous success stories and a brief recap of the most common concepts found in machine learning. Then, we introduce neural networks and the optimization techniques to train them. We’ll show you how to get ready with Keras API to start training deep learning models, both on CPU and on GPU. Then, we present two types of neural architecture: convolutional and recurrent neural networks

First, we present a well-known use case of deep learning: recommender systems, where we try to predict the "rating" or "preference" that a user would give to an item. Then, we introduce an interesting subject called style transfer. Deep learning has this ability to transform images based on a set of inputs, so we’ll morph an image with a style image to combine them into a very realistic result. In the third section, we present techniques to train on very small datasets. This comprises transfer learning, data augmentation, and hyperparameter search, to avoid overfitting and to preserve the generalization property of the network.

Finally, we complete this course by what Yann LeCun, Director at Facebook, considered as the biggest breakthrough in Machine Learning of the last decade: Generative Adversarial Networks. These networks are amazingly good at capturing the underlying distribution of a set of images to generate new images.

Table of Contents

  1. Chapter 1 : Introduction to Deep Learning
    1. The Course Overview 00:02:16
    2. What is Deep Learning? 00:05:13
    3. Machine Learning Concepts 00:23:55
    4. Foundations of Neural Networks 00:09:49
    5. Optimization 00:11:33
  2. Chapter 2 : Get Started with Keras
    1. Configuration of Keras 00:08:15
    2. Presentation of Keras and Its API 00:19:43
    3. Design and Train Deep Neural Networks 00:13:13
    4. Regularization in Deep Learning 00:11:28
  3. Chapter 3 : Convolutional and Recurrent Neural Networks
    1. Introduction to Computer Vision 00:07:57
    2. Convolutional Networks 00:08:20
    3. CNN Architectures 00:06:15
    4. Image Classification Example 00:06:45
    5. Image Segmentation Example 00:04:43
    6. Introduction to Recurrent Networks 00:04:17
    7. Recurrent Neural Networks 00:06:40
    8. “One to Many” Architecture 00:03:33
    9. “Many to One” Architecture 00:07:33
    10. “Many to Many” Architecture 00:07:52
    11. Embedding Layers 00:07:51
  4. Chapter 4 : Recommender Systems
    1. What are Recommender Systems? 00:04:44
    2. Content/Item Based Filtering 00:07:50
    3. Collaborative Filtering 00:12:29
    4. Hybrid System 00:06:28
  5. Chapter 5 : Neural Style Transfer
    1. Introduction to Neural Style Transfer 00:05:24
    2. Single Style Transfer 00:04:16
    3. Advanced Techniques 00:07:51
    4. Style Transfer Explained 00:11:04
  6. Chapter 6 : Advanced Techniques
    1. Data Augmentation 00:05:00
    2. Transfer Learning 00:15:56
    3. Hyper Parameter Search 00:08:39
    4. Natural Language Processing 00:10:28
  7. Chapter 7 : Generative Adversarial Networks
    1. An Introduction to Generative Adversarial Networks (GAN) 00:08:54
    2. Run Our First GAN 00:09:34
    3. Deep Convolutional Generative Adversarial Networks (DCGAN) 00:05:50
    4. Techniques to Improve GANs 00:10:00