Image by Editor
 

I recently wrote an article compiling free machine learning and deep learning ebooks. It was well-received, and so I have decided to follow up with a second installation.

If you’re interested in delving into the intricacies of deep learning and want some FREE resources, carry on reading.

 

Deep Learning: Technical Introduction

 

By Thomas Epelbaum

This ebook goes through the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. You will gain a deeper understanding of each architecture to help build your deep learning knowledge.

Click here to read

 

Neural Networks and Deep Learning

 

By Charu C. Aggarwal

Neural Networks and deep learning - pretty much all you need to know about deep learning. In this book, you will start with the foundations of neural networks and its basic architecture and then move on to the intricacies of training a neural network, and more. 

Click here to read

 

Neural Networks and Deep Learning 

 

By Michael Nielsen

In this ebook, you will learn how to use neural nets to recognize handwritten digits, how the backpropagation algorithm works, improving the way neural networks learn, a visual proof that neural nets can compute any function, why deep neural networks are hard to retrain, and more foundations of deep learning.

Click here to read

 

Dive into Deep Learning

 

By Aston Zhang, Zachary C. Lipton, Mi Li, and Alexander J. Smole

This e-book not only gives you a great overview of deep learning, but it starts with the foundations and the depths of machine learning. It takes you on a journey by first understanding machine learning before getting into the application of neural networks and deep learning. A deep book that covers pretty much everything.

Click here to read

 

Neural Network Design

 

By Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale, and Orlando De Jesús

In this ebook, you will first start with understanding the foundations of the Neuron Model and Network Architectures and then further go into the perceptron learning rule. You will then get more theory around vector spaces, linear transformation, and more.

Click here to read

 

Deep Learning Methods and Applications

 

By Li Deng and Dong Yu

Created by Microsoft researchers Li Deng and Dong Yu, this ebook gives you an overview of the methodologies behind deep learning and their different types of applications. You will go further into speech and audio processing, NLP, information retrieval, and more.

Click here to read

 

Applied Deep Learning

 

By Umberto Michelucci

This ebook is a case-based approach to understanding Deep Neural Networks. Chapters include computational graphs and TensorFlow, single neurons, feedforward neural networks, training neural networks, regularization, metric analysis, hyperparameter tuning, convolutional and recurrent neural networks, logistic regression from scratch, and a research project.

Click here to read

 

Advanced Applications for Artificial Neural Networks

 

By Adel El-Shahat

??Researchers put their brains together and came to write this book about the importance of artificial neural networks and their advanced applications. It provides case studies such as hardware ANN for gait generation of multi-legged robots, production of high-resolution soil property ANN maps, and more. If you’re interested in knowing more about the current capabilities of artificial neural networks, and what they can do in the future - this is a book for you. 

Click here to read

 

Deep Learning Interviews: Problems and Solutions

 

By Shlomo Kashani

Learning and being able to apply the content is always what people think is the most difficult part. When in fact, being able to ace the interview that gets you the job you’ve always wanted is the real challenge. This ebook goes through real-world deep-learning interview problems and solutions to help you prepare.

Click here to read

 

Physics-based Deep Learning

 

By N. Thuerey, P. Holl, M. Mueller, P. Schnell, F. Trost, and K. Um

This ebook goes through the practical and comprehensive introduction of deep learning in the context of physical simulations. You are provided with hands-on code examples using Jupyter notebooks. Topics include physical losses, differentiable physics, NNS, reinforcement learning, and more.

Click here to read

 

Deep Learning

 

By Ian Goodfellow, Yoshua Bengio, and Aaron Courville

This ebook has two sections, the first starting off with Math and the basics of machine learning and the second moving into deep neural networks. You will be able to transition from machine learning to deep learning and understand how they apply to one another. You also have access to exercises and lectures to cater to your study needs. 

Click here to read

 

Deep Learning on Graphs 

 

By Yao Ma and Jiliang Tang

Graphs have been used to represent data for a very long time now. It’s easily interpretable, explainable, and simple. This ebook goes into the importance of graphs in the representation of deep learning as well as going in-depth on the foundations, methods, applications, and advances.

Click here to read

 

Deep Learning for Coders with Fastai and Pytorch: AI Applications Without a PhD

 

By Howard, J. and Gugger, S.

This ebook on GitHub has many chapters, but as we are focusing on deep learning I will attach the link for that - but feel free to have a gander at the other chapters available. In the deep learning chapter, you will understand more about neural networks and how the Jupyter notebook works. It focuses on the fastai deep learning library and how you can walk through it with them and get a more practical understanding of deep learning. 

Click here to read.

 

Explanatory Model Analysis: Explore, Explain, and Examine Predictive Models 

 

By Przemyslaw Biecek and Tomasz Burzykowski

Explaining the analysis of a model is a skill in itself. It’s the skill you need to help a business make the right decision for the company to improve and continuously grow. Companies need people with these skills!

Click here to read. 

 

Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning 

 

By Jean Gallier and Jocelyn Quaintance

If you want to learn more about Mathematics and how it applies to Computer Science and Machine Learning - this is what you need to read. It is a deep ebook that goes through math in so much depth that once you finish this book, I'm convinced you will have graduated with a master's in Math.

Click here to read

 

Wrapping it up

 

Deep learning and machine learning are one, so if you are struggling with understanding the concept of deep learning you may need to go back and review machine learning. Check out the previous installment of free machine learning and deep learning books.

 
 
Nisha Arya is a Data Scientist and Freelance Technical Writer. She is particularly interested in providing Data Science career advice or tutorials and theory-based knowledge around Data Science. She also wishes to explore the different ways Artificial Intelligence is/can benefit the longevity of human life. A keen learner, seeking to broaden her tech knowledge and writing skills, whilst helping guide others.