Автор: Goodfellow Ian, Bengio Yoshua, Courville Aaron Название: Deep Learning ISBN: 0262035618 ISBN-13(EAN): 9780262035613 Издательство: MIT Press Рейтинг: Цена: 13543.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание:
An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives.
"Written by three experts in the field, Deep Learning is the only comprehensive book on the subject." -- Elon Musk, cochair of OpenAI; cofounder and CEO of Tesla and SpaceX
Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning.
The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models.
Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
Автор: Sutton Richard S., Barto Andrew G. Название: Reinforcement Learning: An Introduction, 2 ed. ISBN: 0262039249 ISBN-13(EAN): 9780262039246 Издательство: MIT Press Рейтинг: Цена: 18850.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание:
The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence.
Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics.
Like the first edition, this second edition focuses on core, online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new for the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.
This book is for physics students interested in the mathematics they use and for mathematics students interested in seeing how some of the ideas of their discipline find realization in an applied setting. The presentation tries to strike a balance between formalism and application, between abstract and concrete. The interconnections among the various topics are clarified both by the use of vector spaces as a central unifying theme, recurring throughout the book, and by putting ideas into their historical context. Enough of the essential formalism is included to make the presentation self-contained.
The book is divided into eight parts: The first covers finite- dimensional vector spaces and the linear operators defined on them. The second is devoted to infinite-dimensional vector spaces, and includes discussions of the classical orthogonal polynomials and of Fourier series and transforms. The third part deals with complex analysis, including complex series and their convergence, the calculus of residues, multivalued functions, and analytic continuation. Part IV treats ordinary differential equations, concentrating on second-order equations and discussing both analytical and numerical methods of solution. The next part deals with operator theory, focusing on integral and Sturm--Liouville operators. Part VI is devoted to Green's functions, both for ordinary differential equations and in multidimensional spaces. Parts VII and VIII contain a thorough discussion of differential geometry and Lie groups and their applications, concluding with Noether's theorem on the relationship between symmetries and conservation laws.
Intended for advanced undergraduates or beginning graduate students, this comprehensive guide should also prove useful as a refresher or reference for physicists and applied mathematicians. Over 300 worked-out examples and more than 800 problems provide valuable learning aids.
Numerous enhancements and revision are incorporated into this new edition. For example, fiber bundle techniques are used to introduce differential geometry. This more elegant and intuitive approach naturally connects differential geometry with not only the general theory of relativity, but also gauge theories of fundamental forces.
Some praise for the previous edition:
PAGEOPH Pure and Applied Geophysics]
Review by Daniel Wojcik, University of Maryland
"This volume should be a welcome addition to any collection. The book is well written and explanations are usually clear. Lives of famous mathematicians and physicists are scattered within the book. They are quite extended, often amusing, making nice interludes. Numerous exercises help the student practice the methods introduced. ... I have recently been using this book for an extended time and acquired a liking for it. Among all the available books treating mathematical methods of physics this one certainly stands out and assuredly it would suit the needs of many physics readers."
ZENTRALBLATT MATH
Review by G.Roepstorff, University of Aachen, Germany
..". Unlike most existing texts with the same emphasis and audience, which are merely collections of facts and formulas, the present book is more systematic, self-contained, with a level of presentation that tends to be more formal and abstract. This entails proving a large number of theorems, lemmas, and corollaries, deferring most of the applications that physics students might be interested in to the example sections in small print. Indeed, there are 350 worked-out examples and about 850 problems. ... A very nice feature is the way the author intertwines the formalism with the life stories and anecdotes of some mathematicians and physicists, leading at their times. As is often the case, the historical view point helps to understand and appreciate the ideas presented in the text. ... For the physics studen
Автор: Davis Mark H A Название: Mathematical Finance: A Very Short Introduction ISBN: 0198787944 ISBN-13(EAN): 9780198787945 Издательство: Oxford Academ Рейтинг: Цена: 1582.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: Now a vital part of modern economies, the rapid growth of the finance industry in recent decades is largely due to the development of mathematical methods such as the theory of arbitrage. Asset valuation, credit trading, and fund management, now depend on these mathematical tools. Mark Davis explains the theories and their applications.
Автор: Kantorovich Lev Название: Quantum Theory of the Solid State: An Introduction ISBN: 1402021534 ISBN-13(EAN): 9781402021534 Издательство: Springer Рейтинг: Цена: 18284.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: The book targets a broad readership. First of all, it targets young researchers (postgraduate students) in solid state physics (both physicists and theoretical chemists) as it contains a wide and comprehensive coverage of all important branches of the subject including an up-to-date survey of recent revolutionary advances in quantum mechanics which have made it possible not only to calculate many properties of molecules and solids in close agreement with experiment, but to make reliable predictions in cases when a direct experiment is not possible (e.g. the Earth core). Secondly, it should be a valuable asset to established researchers in the areas of materials science, solid-state physics and chemistry due to very detailed explanations of a wide range of phenomena ranging from symmetry, lattice vibrations, electronic structure and superconductivity to magnetic and dielectric properties. Rigour and detail in explaining complicated mathematical techniques and in providing derivations when talking of various physical concepts are essential for those who would like to really understand things they have never had a chance to. Because of that and of the fact that the book contains a lot of material from different areas of solid-state physics retold from a single viewpoint, it should be indispensable for lecturers. Not only a number of courses, both general and specialised, should be possible to set up, but these courses may also be of a different level of difficulty ranging from undergraduate, postgraduate and then to highly advanced ones. This is because of a clear marking system adopted in the book. Hence, it should also be useful for advanced third- and fourth-year undergraduate students.
Автор: Efron Название: An Introduction to the Bootstrap ISBN: 0412042312 ISBN-13(EAN): 9780412042317 Издательство: Taylor&Francis Рейтинг: Цена: 22968.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: An exploration of the many different bootstrap techniques. It discusses useful statistical techniques through real data examples and covers nonparametric regression, density estimation, classification trees, and least median squares regression. There are numerous exercises.
Автор: Ross Название: An Elementary Introduction to Mathematical Finance ISBN: 0521192536 ISBN-13(EAN): 9780521192538 Издательство: Cambridge Academ Рейтинг: Цена: 9186.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: This textbook on the basics of option pricing is accessible to readers with limited mathematical training. It is for both professional traders and undergraduates studying the basics of finance. This third edition includes three new chapters, along with expanded sets of exercises and references for all the chapters.
This book explores image processing from several perspectives: the creative, the theoretical (mainly mathematical), and the programmatical. It explains the basic principles of image processing, drawing on key concepts and techniques from mathematics, psychology of perception, computer science, and art, and introduces computer programming as a way to get more control over image processing operations. It does so without requiring college-level mathematics or prior programming experience. The content is supported by PixelMath, a freely available software program that helps the reader understand images as both visual and mathematical objects.
The first part of the book covers such topics as digital image representation, sampling, brightness and contrast, color models, geometric transformations, synthesizing images, stereograms, photomosaics, and fractals. The second part of the book introduces computer programming using an open-source version of the easy-to-learn Python language. It covers the basics of image analysis and pattern recognition, including edge detection, convolution, thresholding, contour representation, and K-nearest-neighbor classification. A chapter on computational photography explores such subjects as high-dynamic-range imaging, autofocusing, and methods for automatically inpainting to fill gaps or remove unwanted objects in a scene. Applications described include the design and implementation of an image-based game. The PixelMath software provides a "transparent" view of digital images by allowing the user to view the RGB values of pixels by zooming in on an image. PixelMath provides three interfaces: the pixel calculator; the formula page, an advanced extension of the calculator; and the Python window.
Автор: Francois-Lavet Vincent, Henderson Peter, Islam Riashat Название: An Introduction to Deep Reinforcement Learning ISBN: 1680835386 ISBN-13(EAN): 9781680835380 Издательство: Неизвестно Рейтинг: Цена: 13656.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: Provides a starting point for understanding deep reinforcement learning. Although written at a research level it provides a comprehensive and accessible introduction to deep reinforcement learning models, algorithms and techniques.
If you are looking for a complete beginners guide to learn deep learning with examples, in just a few hours, then you need to continue reading.
This book delves into the basics of deep learning for those who are enthusiasts concerning all things machine learning and artificial intelligence. For those who have seen movies that show computer systems taking over the world like, Terminator, or benevolent systems that watch over the population, i.e. Person of Interest, this should be right up your alley.
This book will give you the basics of what deep learning entails. That means frameworks used by coders and significant components and tools used in deep learning, that enable facial recognition, speech recognition, and virtual assistance. Yes, deep learning provides the tools through which systems like Siri became possible.
Grab your copy today and learn:
Deep learning utilizes frameworks that allow people to develop tools that are able to offer better abstraction, along with simplification of hard programming issues. TensorFlow is the most popular tool and is used by corporate giants such as Airbus, Twitter, and even Google.
The book illustrates TensorFlow and Caffe2 as the prime frameworks that are used for development by Google and Facebook. Facebook illustrates Caffe2 as one of the lightweight and modular deep learning frameworks, though TensorFlow is the most popular one, considering it has a lot of popularity, and thus, a big forum, which allows for assistance on main problems.
The book considers several components and tools of deep learning such as the neural networks; CNNs, RNNs, GANs, and auto-encoders. These algorithms create the building blocks which propel deep learning and advance it.
The book also considers several applications, including chatbots and virtual assistants, which have become the main focus for deep learning into the future, as they represent the next frontier in information gathering and connectivity. The Internet of Things is also represented here, as deep learning allows for integration of various systems via an artificial intelligence system, which is already being used for the home and car functions.
And much more...
The use of data science adds a lot of value to businesses, and we will continue to see the need for data scientists grow.
This book is probably one of the best books for beginners. It's a step-by-step guide for any person who wants to start learning deep learning and artificial intelligence from scratch.
When data science can reduce spending costs by billions of dollars in our economy, why wait to jump in?
Автор: Charniak Eugene Название: Introduction to Deep Learning ISBN: 0262039516 ISBN-13(EAN): 9780262039512 Издательство: MIT Press Рейтинг: Цена: 5925.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание:
A project-based guide to the basics of deep learning.
This concise, project-driven guide to deep learning takes readers through a series of program-writing tasks that introduce them to the use of deep learning in such areas of artificial intelligence as computer vision, natural-language processing, and reinforcement learning. The author, a longtime artificial intelligence researcher specializing in natural-language processing, covers feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, unsupervised models, and other fundamental concepts and techniques. Students and practitioners learn the basics of deep learning by working through programs in Tensorflow, an open-source machine learning framework. "I find I learn computer science material best by sitting down and writing programs," the author writes, and the book reflects this approach.
Each chapter includes a programming project, exercises, and references for further reading. An early chapter is devoted to Tensorflow and its interface with Python, the widely used programming language. Familiarity with linear algebra, multivariate calculus, and probability and statistics is required, as is a rudimentary knowledge of programming in Python. The book can be used in both undergraduate and graduate courses; practitioners will find it an essential reference.
ООО "Логосфера " Тел:+7(495) 980-12-10 www.logobook.ru
