by Tsvetoslav Tsekov | Released January 2018 | ISBN: 9781788624688

Learn to build cutting-edge Deep Learning models in a simple, easy to understand way.About This VideoCovers practical projects on building and training deep learning models with KerasCombines theory and practice, giving you a solid foundation to build your own Deep Leaning models.Implement state of the art CNNs, RNNs, Autoencoders and Generative Adversarial ModelsIn DetailKeras is a deep learning library for fast, efficient training of deep learning models, and can also work with Tensorflow and Theano. Because it is lightweight and very easy to use, Keras has gained quite a lot of popularity in a very short time.This course will show you how to leverage the power of Keras to build and train high performance, high accuracy deep learning models, by implementing practical projects in real-world domains.Spanning over three hours, this course will help you master even the most advanced concepts in deep learning and how to implement them with Keras. You will train CNNs, RNNs, LSTMs, Autoencoders and Generative Adversarial Networks using real-world training datasets.These datasets will be from domains such as Image Processing and Computer Vision, Natural Language Processing, Reinforcement Learning and more.By the end of this highly practical course, you will be well-versed with deep learning and its implementation with Keras. Show and hide more

1. Chapter 1 : Introduction to Jupyter Notebooks and Data Shapes
   • The Course Overview 00:02:29
   • Jupyter Notebook Basics 00:03:38
   • Data Shapes 00:03:45
2. Chapter 2 : Neural Network for House Price Prediction
   • Neural Networks and How They Are Implemented with Keras 00:10:19
   • Building Connected Layers and Applying Activation Functions 00:10:01
   • Applying Loss Functions and Optimizers for Backpropagation 00:09:44
   • Advanced Implementation with Keras 00:04:00
   • Training the Model 00:06:17
   • Testing the Model 00:03:14
   • Metrics and Improving Performance 00:07:28
3. Chapter 3 : Convolutional Neural Network for Image Classification
   • Concepts of CNNs 00:04:54
   • Applying Filters, Strides, Padding, and Pooling 00:06:00
   • Basic Implementation with Keras 00:06:35
   • Leaky Rectified Linear Units 00:02:16
   • Dropout 00:02:58
   • Advanced Implementation with Keras 00:02:28
   • Training the Model 00:02:58
   • Testing the Model and Metrics 00:03:43
   • Transfer Learning 00:08:12
4. Chapter 4 : Convolutional Autoencoder for Image Denoising
   • Concepts and Applications of Autoencoders 00:03:10
   • Basic Implementation with Keras 00:04:30
   • Advanced Implementation with Keras 00:01:53
   • Convolutional Autoencoder with Keras 00:02:55
   • Training the Model 00:02:14
   • Testing the Model 00:02:20
5. Chapter 5 : Recurrent Neural Network for Machine Translation
   • Concepts of RNNs, LSTM Cells, and GRU Cells 00:08:41
   • Data Preprocessing 00:02:41
   • Building a Simple RNN Model in Keras 00:04:24
   • Advanced Implementation with Keras 00:03:39
   • Training the Model 00:02:26
   • Testing the Model 00:05:03
6. Chapter 6 : Convolutional GAN for Image Generation
   • Concepts and Applications of GANs 00:04:06
   • Batch Normalization 00:02:44
   • Convolutional GAN with Keras 00:05:50
   • Training the Model 00:03:16
   • Testing the Model 00:02:39
Show and hide more