by Indra den Bakker | Released June 2018 | ISBN: 9781789531602

Over 20 practical videos on neural network modeling, reinforcement learning, and transfer learning using PythonAbout This VideoPractical video on training different neural network models and fine-tuning them for optimal performanceUse Python frameworks such as TensorFlow, Caffe, Keras, and Theano for Natural Language Processing, Computer Vision, and moreA hands-on guide covering the common (and not so common) problems in Deep Learning using Python In DetailDeep Learning is revolutionizing a wide range of industries. For many applications, Deep Learning has been proven to outperform humans by making faster and more accurate predictions. This course provides a top-down and bottom-up approach to demonstrating Deep Learning solutions to real-world problems in different areas. These applications include Computer Vision, Generative Adversarial Networks, and time series. This course presents technical solutions to the issues presented, along with a detailed explanation of the solutions. Furthermore, it provides a discussion on the corresponding pros and cons of implementing the proposed solution using a popular framework such as TensorFlow, PyTorch, and Keras. The course includes solutions that are related to the basic concepts of neural networks; all techniques, as well as classical network topologies, are covered. The main purpose of this video course is to provide Python programmers with a detailed list of solutions so they can apply Deep Learning to common and not-so-common scenarios.All the code and supporting files for this course are available on Github at https://github.com/PacktPublishing/Python-Deep-Learning-Solutions Show and hide more

1. Chapter 1 : Deep Learning Frameworks
   • The course overview 00:02:43
   • Understanding TensorFlow, Keras and PyTorch Framework 00:06:31
   • Deep Learning Using CNTK and Gluon Framework 00:02:38
2. Chapter 2 : Feed-Forward Neural Networks
   • Implementing Single and Multi-Layer Neural Network 00:07:22
   • Experiment with Activation Functions, Hidden Layers, and Hidden Units 00:06:19
   • Autoencoder, Loss Function, and Optimizers 00:06:25
   • Overfitting Prevention Methods 00:04:13
3. Chapter 3 : Convolutional and Recurrent Neural Networks
   • Optimization Techniques for CNNs 00:05:43
   • Experimenting with Different Types of Initialization 00:07:55
   • Implementing Simple RNN and LSTM 00:04:50
   • Implementing GRUs and Bidirectional RNNs 00:04:18
4. Chapter 4 : GANs and Computer Vision
   • Implementing Generative Adversarial Networks 00:04:14
   • Computer Vision Techniques 00:05:53
   • Detecting Facial Key Points and Transferring Styles 00:03:17
5. Chapter 5 : Neural Network Learning and Data Processing
   • Hyper Parameter Selection and Tuning 00:05:21
   • Speech Recognition 00:05:41
   • Time Series and Structured Data 00:07:02
6. Chapter 6 : Network Internals and Pretrained Models
   • Visualizing and Analysing Network 00:04:51
   • Freezing and Storing the Network 00:02:51
   • Using InceptionV3 and ResNet50 Model 00:02:52
   • Leveraging VGG Model and Fine Tuning 00:05:00
Show and hide more