Python Deep Learning Cookbook.

✍ Scribed by Bakker, Indra den

• Publisher: Packt Publishing
• Year: 2017
• Tongue: English
• Leaves: 435
• Category: Library

✦ Synopsis

Solve different problems in modelling deep neural networks using Python, Tensorflow, and Keras with this practical guide About This Book 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 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. Thorough understanding of the machine learning concepts and Python libraries such as NumPy, SciPy and scikit-learn is expected. Additionally, basic knowledge in linear algebra and calculus is desired. 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 In Detail 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. Style and approach Unique blend of independent recipes arranged in the most logical manner Downloading the example code for...  Read more...

✦ Table of Contents

""Cover ""
""Copyright""
""Credits""
""About the Author""
""About the Reviewer""
""www.PacktPub.com""
""Customer Feedback""
""Table of Contents""
""Preface""
""Chapter 1: Programming Environments, GPU Computing, Cloud Solutions, and Deep Learning Frameworks ""
""Introduction""
""Setting up a deep learning environment""
""How to do it ... ""
""Launching an instance on Amazon Web Services (AWS)""
""Getting ready""
""How to do it ... ""
""Launching an instance on Google Cloud Platform (GCP)""
""Getting ready""
""How to do it ... ""
""Installing CUDA and cuDNN""
""Getting ready"" ""How to do it ... """"Installing Anaconda and libraries""
""How to do it ... ""
""Connecting with Jupyter Notebooks on a server""
""How to do it ... ""
""Building state-of-the-art, production-ready models with TensorFlow""
""How to do it ... ""
""Intuitively building networks with Keras ""
""How to do it ... ""
""Using PyTorchâ#x80
#x99
s dynamic computation graphs for RNNs""
""How to do it ... ""
""Implementing high-performance models with CNTK""
""How to do it ... ""
""Building efficient models with MXNet""
""How to do it ... ""
""Defining networks using simple and efficient code with Gluon"" ""How to do it ... """"Chapter 2: Feed-Forward Neural Networks ""
""Introduction""
""Understanding the perceptron""
""How to do it ... ""
""Implementing a single-layer neural network""
""How to do it ... ""
""Building a multi-layer neural network""
""How to do it ... ""
""Getting started with activation functions""
""How to do it ... ""
""Experiment with hidden layers and hidden units""
""How to do it ... ""
""There's more ... ""
""Implementing an autoencoder""
""How to do it ... ""
""Tuning the loss function""
""How to do it ... ""
""Experimenting with different optimizers"" ""How to do it ... """"Improving generalization with regularization""
""How to do it ... ""
""Adding dropout to prevent overfitting""
""How to do it ... ""
""Chapter 3: Convolutional Neural Networks ""
""Introduction""
""Getting started with filters and parameter sharing""
""How to do it ... ""
""Applying pooling layers""
""How to do it ... ""
""Optimizing with batch normalization""
""How to do it ... ""
""Understanding padding and strides""
""How to do it ... ""
""Experimenting with different types of initialization""
""How to do it ... ""
""Implementing a convolutional autoencoder"" ""How to do it ... """"Applying a 1D CNN to text""
""How to do it ... ""
""Chapter 4: Recurrent Neural Networks ""
""Introduction""
""Implementing a simple RNN""
""How to do it ... ""
""Adding Long Short-Term Memory (LSTM)""
""How to do it ... ""
""Using gated recurrent units (GRUs)""
""How to do it ... ""
""Implementing bidirectional RNNs""
""How to do it ... ""
""Character-level text generation""
""How to do it ... ""
""Chapter 5: Reinforcement Learning ""
""Introduction""
""Implementing policy gradients""
""Getting ready""
""How to do it ... ""

✦ Subjects

Python (Computer program language)