Название: Demystifying Deep Learning: An Introduction to the Mathematics of Neural Networks
Автор: Douglas J. Santry
Издательство: Wiley-IEEE Press
Год: 2024
Страниц: 259
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

Discover how to train Deep Learning models by learning how to build real Deep Learning software libraries and verification software!

The study of Deep Learning and Artificial Neural Networks (ANN) is a significant subfield of artificial intelligence (AI) that can be found within numerous fields: medicine, law, financial services, and science, for example. Just as the robot revolution threatened blue-collar jobs in the 1970s, so now the AI revolution promises a new era of productivity for white collar jobs. Important tasks have begun being taken over by ANNs, from disease detection and prevention, to reading and supporting legal contracts, to understanding experimental data, model protein folding, and hurricane modeling. AI is everywhere—on the news, in think tanks, and occupies government policy makers all over the world —and ANNs often provide the backbone for AI.

Relying on an informal and succinct approach,Demystifying Deep Learning is a useful tool to learn the necessary steps to implement ANN algorithms by using both a software library applying neural network training and verification software. The volume offers explanations of how real ANNs work, and includes 6 practical examples that demonstrate in real code how to build ANNs and the datasets they need in their implementation, available in open-source to ensure practical usage. This approachable book follows ANN techniques that are used every day as they adapt to Natural Language Processing (NLP), image recognition, problem solving, and generative applications. This volume is an important introduction to the field, equipping the reader for more advanced study.

Interest in Deep Learning (DL) is increasing every day. It has escaped from the research laboratories and become a daily fact of life. The achievements and potential of DL are reported in the lay news and form the subject of discussion at dinner tables, cafes, and pubs across the world. The universe of DL is a veritable alphabet soup of bewildering acronyms. There are artificial neural networks (ANN)s, RNNs, LSTMs, CNNs, Generative Adversarial Networks (GAN)s, and more are introduced every day. The types and applications of DL are proliferating rapidly, and the acronyms grow in number with them. As DL is successfully applied to new problem domains this trend will continue.

DL is based on ANN. Often only neural networks is written and the artificial is implied. ANNs attempt to mathematically model biological assemblies of neurons. The initial goal of research into ANNs was to realize AI in a computer. The motivation and means were to mimic the biological mechanisms of cognitive processes in animal brains. This led to the idea of modeling the networks of neurons in brains. If biological neural networks could be modeled accurately with mathematics, then computers could be programmed with the models. Computers would then be able to perform tasks that were previously thought only possible by humans; the dream of the electronic brain was born. Two problem domains were of particular interest: Natural Language Processing (NLP), and image recognition.

Demystifying Deep Learning readers will also find:
A volume that emphasizes the importance of classification
Discussion of why ANN libraries, such as Tensor Flow and Pytorch, are written in C++ rather than Python
Each chapter concludes with a "Projects" page to promote students experimenting with real code
A supporting library of software to accompany the book at GitHub
An approachable explanation of how generative AI, such as generative adversarial networks (GAN), really work.
An accessible motivation and elucidation of how transformers, the basis of large language models (LLM) such as ChatGPT, work.

Demystifying Deep Learning is ideal for engineers and professionals that need to learn and understand ANNs in their work. It is also a helpful text for advanced undergraduates to get a solid grounding on the topic.




ОТСУТСТВУЕТ ССЫЛКА/ НЕ РАБОЧАЯ ССЫЛКА ЕСТЬ РЕШЕНИЕ, ПИШИМ СЮДА!