Neural Networks and Deep Learning by Michael Nielsen.

AuthorMichael Nielsen.
Where you can get itYou can read it for free.
Supplement: You can find the companion code on Github.
Categories: Machine Learning, Deep Learning.

Book abstract:

Neural networks are one of the most beautiful programming paradigms ever invented. In the conventional approach to programming, we tell the computer what to do, breaking big problems up into many small, precisely defined tasks that the computer can easily perform. By contrast, in a neural network we don't tell the computer how to solve our problem. Instead, it learns from observational data, figuring out its own solution to the problem at hand.

Automatically learning from data sounds promising. However, until 2006 we didn't know how to train neural networks to surpass more traditional approaches, except for a few specialized problems. What changed in 2006 was the discovery of techniques for learning in so-called deep neural networks. These techniques are now known as deep learning. They've been developed further, and today deep neural networks and deep learning achieve outstanding performance on many important problems in computer vision, speech recognition, and natural language processing. They're being deployed on a large scale by companies such as Google, Microsoft, and Facebook.

The purpose of this book is to help you master the core concepts of neural networks, including modern techniques for deep learning. After working through the book you will have written code that uses neural networks and deep learning to solve complex pattern recognition problems. And you will have a foundation to use neural networks and deep learning to attack problems of your own devising

Ian Goodfellow, Yoshua Bengio, Aaron Courville - Deep Learning (2017, MIT)

Ian Goodfellow, Yoshua Bengio, Aaron Courville - Deep Learning (2017, MIT)

AuthorsIan GoodfellowYoshua BengioAaron Courville.
Where you can get itBuy on Amazon or read here for free.
Supplement: You can also find lectures with slides and exercises (Github repo).
Category: Deep Learning.

This book is widely considered to the "Bible" of Deep Learning. Written by three experts, including one of the godfathers of the field, this is the most comprehensive book you can find. The book is quite technical but the authors do a great job of explaining everything you need to know to get started.


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.


Data Science From Scratch (Book by David Park )

Data Science From Scratch (Book by David Park )

Data science is the application of a combination of mathematical, statistical, analytical and programming skills for the collection, organization, and interpretation of data to allow effective and proper management of the business whose data it is. The job of such a scientist is trending all over the world. The demand for such scientists is huge, more than the number of available candidates. A recent report explained that the need for these scientists has increased by more than 50% since last year. These scientists often referred to as big data wranglers, are a perfect blend of mathematician and computer scientist. Data science is a field of study that is growing at a fast pace. From big tech companies to E-commerce companies to websites and many others are now relying on data science. The amount of data that is collected by these companies is without any bounds. Semi-structure to big unstructured data is stored in large frameworks of these companies. Now the question is how to use this. What you will gain as knowledge in this book:
  1. Why Is Data Science Widely Used?
  2. Why Should You Study Data Science?
  3. Why Should One Consider Data Science As A Career?
  4. Data Science: An Exciting Career Option
  5. Types of Data Loss and Recovery Options
  6. Data Science and Its Wide Range of Applications
  7. What Are the Programming Languages Required for Data Science?
  8. Meaning of Data Science in Depth
  9. 4 Weird Ways How Data Is Used Around the World
  10. 5 Reasons Why Data Science Could Be the Advertising Wave of the Future
  11. It is a field where one should be trained and practiced. Without proper training and applicative skills, one cannot be as successful as a data scientist. There is a lot to learn about various data science tools and techniques.
  12. Getting certified will not only help you hone your skills but also will confirm your future as a data scientist

View on Amazon