Kirjahaku

The brain has always had a fundamental advantage over conventional computers: it can learn. However, a new generation of artificial intelligence algorithms, in the form of deep neural networks, is rapidly eliminating that advantage. Deep neural networks rely on adaptive algorithms to master a wide variety of tasks, including cancer diagnosis, object recognition, speech recognition, robotic control, chess, poker, backgammon and Go, at super-human levels of performance. In this richly illustrated book, key neural network learning algorithms are explained informally first, followed by detailed mathematical analyses. Topics include both historically important neural networks (e.g. perceptrons), and modern deep neural networks (e.g. generative adversarial networks). Online computer programs, collated from open source repositories, give hands-on experience of neural networks, and PowerPoint slides provide support for teaching. Written in an informal style, with a comprehensive glossary, tutorial appendices (e.g. Bayes' theorem), and a list of further readings, this is an ideal introduction to the algorithmic engines of modern artificial intelligence.

The brain has always had a fundamental advantage over conventional computers: it can learn. However, a new generation of artificial intelligence algorithms, in the form of deep neural networks, is rapidly eliminating that advantage. Deep neural networks rely on adaptive algorithms to master a wide variety of tasks, including cancer diagnosis, object recognition, speech recognition, robotic control, chess, poker, backgammon and Go, at super-human levels of performance. In this richly illustrated book, key neural network learning algorithms are explained informally first, followed by detailed mathematical analyses. Topics include both historically important neural networks (e.g. perceptrons), and modern deep neural networks (e.g. generative adversarial networks). Online computer programs, collated from open source repositories, give hands-on experience of neural networks, and PowerPoint slides provide support for teaching. Written in an informal style, with a comprehensive glossary, tutorial appendices (e.g. Bayes' theorem), and a list of further readings, this is an ideal introduction to the algorithmic engines of modern artificial intelligence.

The brain is the most complex computational machine known to science, even though its components (neurons) are slow and unreliable compared to a laptop computer. In this richly illustrated book, Shannon's mathematical theory of information is used to explore the metabolic efficiency of neurons, with special reference to visual perception. Evidence from a diverse range of research papers is used to show how information theory defines absolute limits on neural efficiency; limits which ultimately determine the neuroanatomical microstructure of the eye and brain. Written in an informal style, with a comprehensive glossary, tutorial appendices, explainer boxes, and a list of annotated Further Readings, this book is an ideal introduction to cutting-edge research in neural information theory.

Modern artificial intelligence (AI) is built upon a relatively small number of foundational research papers, which have been collected and republished in this unique 350-page book. The first chapter provides a summary of the historical roots of AI, and subsequent chapters trace its development, from Rosenblatt's perceptron in 1958 to one of the early GPT models in 2019. Each paper is introduced with a commentary on its historical context and a tutorial-style technical summary. In several chapters, additional context is provided by the paper's original author(s). Written in an informal style, with a comprehensive glossary and tutorial appendices, this book is essential reading for students and researchers who wish to understand the fundamental building blocks of modern AI.

Modern artificial intelligence (AI) is built upon a relatively small number of foundational research papers, which have been collected and republished in this unique 350-page book. The first chapter provides a summary of the historical roots of AI, and subsequent chapters trace its development, from Rosenblatt's perceptron in 1958 to one of the early GPT models in 2019. Each paper is introduced with a commentary on its historical context and a tutorial-style technical summary. In several chapters, additional context is provided by the paper's original author(s). Written in an informal style, with a comprehensive glossary and tutorial appendices, this book is essential reading for students and researchers who wish to understand the fundamental building blocks of modern AI.

Originally developed by Claude Shannon in the 1940s, information theory laid the foundations for the digital revolution, and is now an essential tool in telecommunications, genetics, linguistics, brain sciences, and deep space communication. In this richly illustrated book, accessible examples are used to introduce information theory in terms of everyday games like '20 questions' before more advanced topics are explored. Online MatLab and Python computer programs provide hands-on experience of information theory in action, and PowerPoint slides give support for teaching. Written in an informal style, with a comprehensive glossary and tutorial appendices, this text is an ideal primer for novices who wish to learn the essential principles and applications of information theory.

Originally developed by Claude Shannon in the 1940s, information theory laid the foundations for the digital revolution, and is now an essential tool in telecommunications, genetics, linguistics, brain sciences, and deep space communication. In this richly illustrated book, accessible examples are used to introduce information theory in terms of everyday games like '20 questions' before more advanced topics are explored. Online MatLab and Python computer programs provide hands-on experience of information theory in action, and PowerPoint slides give support for teaching. Written in an informal style, with a comprehensive glossary and tutorial appendices, this text is an ideal primer for novices who wish to learn the essential principles and applications of information theory. Second Edition.

Originally developed by Claude Shannon in the 1940s, information theory laid the foundations for the digital revolution, and is now an essential tool in telecommunications, genetics, linguistics, brain sciences, and deep space communication. In this richly illustrated book, accessible examples are used to introduce information theory in terms of everyday games like '20 questions' before more advanced topics are explored. Online MatLab and Python computer programs provide hands-on experience of information theory in action, and PowerPoint slides give support for teaching. Written in an informal style, with a comprehensive glossary and tutorial appendices, this text is an ideal primer for novices who wish to learn the essential principles and applications of information theory.

This short and richly illustrated book introduces the essential mathematics required to understand information theory. Originally developed by Claude Shannon in the 1940s, information theory laid the foundations for the digital revolution, and is now an essential tool in telecommunications, genetics, linguistics, brain sciences, and deep space communication. Accessible examples are used to introduce information theory in terms of everyday games like "20 questions" before more advanced topics are explored. Online Matlab and Python computer code provides hands-on experience of information theory in action. Written in an informal style, with a comprehensive glossary, this concise text is an ideal primer for novices who wish to gain a firm grasp of the essential principles of information theory.

This short and richly illustrated book introduces the essential mathematics required to understand information theory. Originally developed by Claude Shannon in the 1940s, information theory laid the foundations for the digital revolution, and is now an essential tool in telecommunications, genetics, linguistics, brain sciences, and deep space communication. Accessible examples are used to introduce information theory in terms of everyday games like "20 questions" before more advanced topics are explored. Online Matlab and Python computer code provides hands-on experience of information theory in action. Written in an informal style, with a comprehensive glossary, this concise text is an ideal primer for novices who wish to gain a firm grasp of the essential principles of information theory.

Artificial intelligence (AI) has now mastered tasks which could, until recently, be performed only by humans. These tasks include cancer diagnosis, drug design, object recognition, speech recognition, chess, backgammon and Go, which AI systems perform at super-human levels of performance. This richly illustrated book is a brief but comprehensive overview (without equations) of current AI systems, how they work, their applications, and their limitations. Artificial neural networks, which are the engines of AI, are introduced in the context of deep learning algorithms. After surveying the impressive capabilities of AI systems on certain tasks, the limited ability of AI to perform tasks that humans find trivial is discussed. The strengths and weaknesses of the key neural network learning algorithms employed by AI are then described. Finally, the question of whether AI systems can be intelligent is discussed, along with the controversial issue of machine consciousness. Written in an informal style, with a comprehensive Glossary and a list of Further Readings, this book represents an ideal introduction to the rapidly evolving field of AI.

The Fourier transform is a fundamental tool in the physical sciences, with applications in communications theory, electronics, engineering, biophysics and quantum mechanics. In this brief book, the essential mathematics required to understand and apply Fourier analysis is explained. The tutorial style of writing, combined with over 60 diagrams, offers a visually intuitive and rigorous account of Fourier methods. Hands-on experience is provided in the form of simple examples, written in Python and Matlab computer code. Supported by a comprehensive Glossary and an annotated list of Further Readings, this represents an ideal introduction to the Fourier transform.

The Fourier transform is a fundamental tool in the physical sciences, with applications in communications theory, electronics, engineering, biophysics and quantum mechanics. In this brief book, the essential mathematics required to understand and apply Fourier analysis is explained. The tutorial style of writing, combined with over 60 diagrams, offers a visually intuitive and rigorous account of Fourier methods. Hands-on experience is provided in the form of simple examples, written in Python and Matlab computer code. Supported by a comprehensive Glossary and an annotated list of Further Readings, this represents an ideal introduction to the Fourier transform.

Linear regression is the workhorse of data analysis. It is the first step, and often the only step, in fitting a simple model to data. This brief book explains the essential mathematics required to understand and apply regression analysis. The tutorial style of writing, accompanied by over 30 diagrams, offers a visually intuitive account of linear regression, including a brief overview of nonlinear and Bayesian regression. Hands-on experience is provided in the form of numerical examples, included as Matlab code at the end of each chapter, and implemented online as Python and Matlab code. Supported by a comprehensive glossary and tutorial appendices, this book provides an ideal introduction to regression analysis.

Linear regression is the workhorse of data analysis. It is the first step, and often the only step, in fitting a simple model to data. This brief book explains the essential mathematics required to understand and apply regression analysis. The tutorial style of writing, accompanied by over 30 diagrams, offers a visually intuitive account of linear regression, including a brief overview of nonlinear and Bayesian regression. Hands-on experience is provided in the form of numerical examples, included as Python code at the end of each chapter, and implemented online as Python and Matlab code. Supported by a comprehensive glossary and tutorial appendices, this book provides an ideal introduction to regression analysis.