With an increasing interest in AI around the world, deep learning has attracted a great deal of public attention. Every day, deep-learning algorithms are used broadly across different industries. This book will give you all the practical information available on the subject, including best practices, using real-world use cases. You will learn to recognize and extract information to increase predictive accuracy and optimize results.
Starting with a quick recap of important machine learning concepts, the book will delve straight into deep learning principles using scikit-learn. Moving ahead, you will learn to use the latest open source libraries, such as Theano, Keras, Google’s TensorFlow, and H2O. Use this guide to uncover the difficulties of pattern recognition, scaling data with greater accuracy, and discussing deep-learning algorithms and techniques. Whether you want to dive deeper into deep learning or want to investigate how to get more out of this powerful technology, you’ll find everything inside.
What this book covers
Chapter 1, Machine Learning – An Introduction, presents different machine learning approaches and techniques and some of their applications to real-world problems. We will introduce one of the major open source packages available in Python for machine learning, scikit-learn.
Chapter 2, Neural Networks, formally introduces what neural networks are. We will thoroughly describe how a neuron works and will see how we can stack many layers to create and use deep feed-forward neural networks.
Chapter 3, Deep Learning Fundamentals, walks you toward an understanding of what deep learning is and how it is related to deep neural networks.
Chapter 4, Unsupervised Feature Learning, covers two of the most powerful and often-used architectures for unsupervised feature learning: auto-encoders and restricted Boltzmann machines.
Chapter 5, Image Recognition, starts from drawing an analogy with how our visual cortex works and introduces convolutional layers, followed up with a descriptive intuition of why they work.
Chapter 6, Recurrent Neural Networks and Language Models, discusses powerful methods that have been very promising in a lot of tasks, such as language modeling and speech recognition.
Chapter 7, Deep Learning for Board Games, covers the different tools used for solving board games such as checkers and chess.
Chapter 8, Deep Learning for Computer Games, looks at the more complex problem of training AI to play computer games.
Chapter 9, Anomaly Detection, starts by explaining the difference and similarities of concepts between outlier detection and anomaly detection. You will be guided through an imaginary fraud case study, followed by examples showing the danger of having anomalies in real-world applications and the importance of automated and fast detection systems.
Chapter 10, Building a Production-Ready Intrusion Detection System, leverages H2O and general common practices to build a scalable distributed system ready for deployment in production. You will learn how to train a deep learning network using Spark and MapReduce, how to use adaptive learning techniques for faster convergence and very important how to validate a model and evaluate the end to end pipeline.