▶Book Description
Deep Learning is revolutionizing a wide range of industries. For many applications, deep learning has proven to outperform humans by making faster and more accurate predictions. This book provides a top-down and bottom-up approach to demonstrate deep learning solutions to real-world problems in different areas. These applications include Computer Vision, Natural Language Processing, Time Series, and Robotics.
The Python Deep Learning Cookbook presents technical solutions to the issues presented, along with a detailed explanation of the solutions. Furthermore, a discussion on corresponding pros and cons of implementing the proposed solution using one of the popular frameworks like TensorFlow, PyTorch, Keras and CNTK is provided. The book includes recipes that are related to the basic concepts of neural networks. All techniques s, as well as classical networks topologies. The main purpose of this book is to provide Python programmers a detailed list of recipes to apply deep learning to common and not-so-common scenarios.
▶What You Will Learn
⦁ Implement different neural network models in Python
⦁ Select the best Python framework for deep learning such as PyTorch, Tensorflow, MXNet and Keras
⦁ Apply tips and tricks related to neural networks internals, to boost learning performances
⦁ Consolidate machine learning principles and apply them in the deep learning field
⦁ Reuse and adapt Python code snippets to everyday problems
⦁ Evaluate the cost/benefits and performance implication of each discussed solution
▶Key Features
⦁ Practical recipes on training different neural network models and tuning them for optimal performance
⦁ Use Python frameworks like TensorFlow, Caffe, Keras, Theano for Natural Language Processing, Computer Vision, and more
⦁ A hands-on guide covering the common as well as the not so common problems in deep learning using Python
▶What you need for this book
This book is focused on AI in Python, as opposed to Python itself. We have used Python 3 to build various applications. We focus on how to utilize various Python libraries in the best possible way to build real-world applications. In that spirit, we have tried to keep all of the code as friendly and readable as possible. We feel that this will enable our readers to easily understand the code and readily use it in different scenarios.
▶Who This Book Is For
This book is intended for machine learning professionals who are looking to use deep learning algorithms to create real-world applications using Python. A thorough understanding of machine learning concepts and Python libraries such as NumPy, SciPy, and scikit-learn is expected. Additionally, basic knowledge of linear algebra and calculus is desired.
▶What this book covers
⦁ Chapter 1, Programming Environments, GPU Computing, Cloud Solutions, and Deep Learning Frameworks, includes information and recipes related to environments and GPU computing. It is a must-read for readers who have issues in setting up their environment on different platforms.
⦁ Chapter 2, Feed-Forward Neural Networks, provides a collection of recipes related to feedforward neural networks and forms the basis for the other chapters. The focus of this chapter is to provide solutions to common implementation problems for different network topologies.
⦁ Chapter 3, Convolutional Neural Networks, focuses on convolutional neural networks and their application in computer vision. It provides recipes on techniques and optimizations used in CNNs.
⦁ Chapter 4, Recurrent Neural Networks, provides a collection of recipes related to recurrent neural networks. These include LSTM networks and GRUs. The focus of this chapter is to provide solutions to common implementation problems for recurrent neural networks.
⦁ Chapter 5, Reinforcement Learning, covers recipes for reinforcement learning with neural networks. The recipes in this chapter introduce the concepts of deep reinforcement learning in a single-agent world.
⦁ Chapter 6, Generative Adversarial Networks, provides a collection of recipes related to unsupervised learning problems. These include generative adversarial networks for image generation and super resolution.
⦁ Chapter 7, Computer Vision, contains recipes related to processing data encoded as images, including video frames. Classic techniques of processing image data using Python will be provided, along with best-of-class solutions for detection, classification, and segmentation.
⦁ Chapter 8, Natural Language Processing, contains recipes related to textual data processing. This includes recipes related to textual feature representation and processing, including word embeddings and text data storage.
⦁ Chapter 9, Speech Recognition and Video Analysis, covers recipes related to stream data processing. This includes audio, video, and frame sequences
⦁ Chapter 10, Time Series and Structured Data, provides recipes related to number crunching. This includes sequences and time series.
⦁ Chapter 11, Game Playing Agents and Robotics, focuses on state-of-the-art deep learning research applications. This includes recipes related to game-playing agents in a multi-agent environment (simulations) and autonomous vehicles.
⦁ Chapter 12, Hyperparameter Selection, Tuning, and Neural Network Learning, illustrates recipes on the many aspects involved in the learning process of a neural network. The overall objective of the recipes is to provide very neat and specific tricks to boost network performance.
⦁ Chapter 13, Network Internals, covers the internals of a neural network. This includes tensor decomposition, weight initialization, topology storage, bottleneck features, and corresponding embedding.
⦁ Chapter 14, Pretrained Models, covers popular deep learning models such as VGG-16 and Inception V4.
