Book Image

Python Deep Learning - Second Edition

By : Ivan Vasilev, Daniel Slater, Gianmario Spacagna, Peter Roelants, Valentino Zocca
Book Image

Python Deep Learning - Second Edition

By: Ivan Vasilev, Daniel Slater, Gianmario Spacagna, Peter Roelants, Valentino Zocca

Overview of this book

With the surge in artificial intelligence in applications catering to both business and consumer needs, deep learning is more important than ever for meeting current and future market demands. With this book, you’ll explore deep learning, and learn how to put machine learning to use in your projects. This second edition of Python Deep Learning will get you up to speed with deep learning, deep neural networks, and how to train them with high-performance algorithms and popular Python frameworks. You’ll uncover different neural network architectures, such as convolutional networks, recurrent neural networks, long short-term memory (LSTM) networks, and capsule networks. You’ll also learn how to solve problems in the fields of computer vision, natural language processing (NLP), and speech recognition. You'll study generative model approaches such as variational autoencoders and Generative Adversarial Networks (GANs) to generate images. As you delve into newly evolved areas of reinforcement learning, you’ll gain an understanding of state-of-the-art algorithms that are the main components behind popular games Go, Atari, and Dota. By the end of the book, you will be well-versed with the theory of deep learning along with its real-world applications.
Table of Contents (12 chapters)

Introduction to machine learning

Machine learning is often associated with terms such as big data and artificial intelligence (AI). However, both are quite different to machine learning. In order to understand what machine learning is and why it's useful, it's important to understand what big data is and how machine learning applies to it.

Big data is a term used to describe huge datasets that are created as the result of large increases in data that is gathered and stored. For example, this may be through cameras, sensors, or internet social sites.

It's estimated that Google alone processes over 20 petabytes of information per day, and this number is only going to increase. IBM estimated that every day, 2.5 quintillion bytes of data is created, and that 90% of all the data in the world has been created in the last two years (https://www.ibm.com/blogs/insights-on-business/consumer-products/2-5-quintillion-bytes-of-data-created-every-day-how-does-cpg-retail-manage-it/).

Clearly, humans alone are unable to grasp, let alone analyze, such huge amounts of data, and machine learning techniques are used to make sense of these very large datasets. Machine learning is the tool used for large-scale data processing. It is well-suited to complex datasets that have huge numbers of variables and features. One of the strengths of many machine learning techniques, and deep learning in particular, is that they perform best when used on large datasets, thus improving their analytic and predictive power. In other words, machine learning techniques, and deep learning neural networks in particular, learn best when they can access large datasets where they can discover patterns and regularities hidden in the data.

On the other hand, machine learning's predictive ability can be successfully adapted to artificial intelligence systems. Machine learning can be thought of as the brain of an AI system. AI can be defined (though this definition may not be unique) as a system that can interact with its environment. Also, AI machines are endowed with sensors that enable them to know the environment they are in, and tools with which they can relate back to the environment. Machine learning is therefore the brain that allows the machine to analyze the data ingested through its sensors to formulate an appropriate answer. A simple example is Siri on an iPhone. Siri hears the command through its microphone and outputs an answer through its speakers or its display, but to do so, it needs to understand what it's being told. Similarly, driverless cars will be equipped with cameras, GPS systems, sonars, and LiDAR, but all this information needs to be processed in order to provide a correct answer. This may include whether to accelerate, brake, or turn. Machine learning is the information-processing method that leads to the answer.

We explained what machine learning is, but what about deep learning (DL)? For now, let's just say that deep learning is a subfield of machine learning. DL methods share some special common features. The most popular representatives of such methods are deep neural networks.