Deep Learning Crash Course for Beginners with Python: Theory and Applications of Artificial Neural Networks, CNN, RNN, LSTM and Autoencoders using . Learning & Data Science for Beginners)

Publishing, AI

ISBN 10: 1734790121 / ISBN 13: 9781734790122

Editore: AI Publishing LLC (edition ), 2020

Riguardo questo articolo

It's a preowned item in almost perfect condition. It has no visible cosmetic imperfections. May come without any shrink wrap; pages are clean and not marred by notes or folds of any kind.

Codice articolo 1734790121-10-1

Dati bibliografici

• Titolo: Deep Learning Crash Course for Beginners with Python: Theory and Applications of Artificial Neural Networks, CNN, RNN, LSTM and Autoencoders using . Learning & Data Science for Beginners)
• Editore: AI Publishing LLC (edition )
• Data di pubblicazione: 2020
• Lingua: Inglese
• ISBN 10: 1734790121
• ISBN 13: 9781734790122
• Rilegatura: Paperback
• Condizione: As New

Descrizione articolo

Riassunto

Artificial intelligence is the rage today!

While you may find it difficult to understand the most recent advancements in AI, it simply boils down to two most celebrated developments: Machine Learning and Deep Learning. In 2020, Deep Learning is leagues ahead because of its supremacy when it comes to accuracy, especially when trained with enormous amounts of data. Deep Learning, essentially, is a subset of Machine Learning, but it’s capable of achieving tremendous power and flexibility. And the era of big data technology presents vast opportunities for incredible innovations in deep learning.

How Is This Book Different?

This book gives equal importance to the theoretical as well as practical aspects of deep learning. You will understand how high-performing deep learning algorithms work. In every chapter, the theoretical explanation of the different types of deep learning techniques is followed by practical examples. You will learn how to implement different deep learning techniques using the TensorFlow Keras library for Python. Each chapter contains exercises that you can use to assess your understanding of the concepts explained in that chapter. Also, in the Resources, the Python notebook for each chapter is provided. The key advantage of buying this book is you get instant access to all the extra content presented with this book—Python codes, references, exercises, and PDFs—on the publisher’s website. You don’t need to spend an extra cent. The datasets used in this book are either downloaded at runtime or are available in the Resources/Datasets folder.

Another advantage is a detailed explanation of the installation steps for the software that you will need to implement the various deep learning algorithms in this book is provided. That is, you get to experiment with the practical aspects of Deep Learning right from page 1. Even if you are new to Python, you will find the crash course on Python programming language in the first chapter immensely useful. Since all the codes and datasets are included with this book, you only need access to a computer with the internet to get started.

The topics covered include:

• Python Crash Course
• Deep Learning Prerequisites: Linear and Logistic Regression
• Neural Networks from Scratch in Python
• Introduction to TensorFlow and Keras
• Convolutional Neural Networks
• Sequence Classification with Recurrent Neural Networks
• Deep Learning for Natural Language Processing
• Unsupervised Learning with Autoencoders
• Answers to All Exercises

Click the BUY button and download the book now to start your Deep Learning journey.