5 Books to Start your Deep Learning Journey in 2020

Sep 8, 2020

Responsive image


No doubt, AI is one of the most crucial future technologies which is being harnessed today and transforming our daily lives. A very important branch of Artificial Intelligence “Deep Learning” has arguably the biggest impact in AI progress. If you’re a beginner looking for the right free resources to learn deep learning and discover applications in fields like Computer Vision, NLP, this plog post is you. This article will introduce the best books to learn deep learning in 2020 and how to practice deep learning with them.

Overview

  • Gentle introduction to Deep Learning
  • Fields of Deep Learning
  • Top 5 Books on Deep Learning (2020)
  • What next after Reading
  • Summary

Now that you have an idea of the steps taking us through this article, Let’s begin with it.

Gentle Introduction to Deep learning

Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.

Ok, so that’s more like a very official definition of deep learning. An easier one you should understand better; Deep learning refers to the various process and methods involving the use of Artificial Neural Networks to build models, functions that learn from real-world data and produce outputs closely related to what they were trained on. Now this is probably a vague definition for it, in the sense that some deep learning models use unsupervised method of mapping functions. I could go around and cite a perfect definition for it, but honestly that is usually rarely important for you and me. If you understand the above definitions, you are very well 60% ahead on what deep learning is all about because anything further than that, is already talking about a specific branch of deep learning like computer vision, natural language processing etc.

Fields of Deep Learning

We come now to a place that we can spend lots of time defining concepts and their differences to each other. The fields or branches of deep learning are many and new theories keeps popping every now and then. This is so because, scientists and researchers are constantly trying to improve upon state-of-the-art models and also achieve new milestones. Several years ago, I should think the world was focusing more on how to improve traditional Machine Learning models and eliminate the repetitive “Rules and Data In - Answers Out” for a scalable solution like “Data and Answers In - Models Out”. Now we have Models that are scalable and more confident in unseen situations. I could still remember when I took the course Machine Learning by Andrew Ng, it was everything I was looking for, I was very happy with it, a few months later I took the course Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning and I could immediately see the huge difference. The difference being using traditional ML methods against Convolutional Neural Networks. Ever since then I’ve been building models with Tensorflow, Keras and high-end libraries for ML & DL in Skicit-learn and python. Why? Because it is so much easier being that models are scalable, eliminates code repetition and is even easier to train.

Not to go out of scope, the field of Deep Learning is diverse and keeps growing, here I would list out a few of the more common ones that I have at one time or other come across. I am not going to be explaining them in detail, this post is more focused on Deep learning and how to get started as a deep learner and the books on deep learning to read that would guide your progress:

  • Computer Vision: Computer Vision, often abbreviated as CV, is defined as a field of study that seeks to develop techniques to help computers “see” and understand the content of digital images such as photographs and videos.The problem of computer vision appears simple because it is trivially solved by people, even very young children. Nevertheless, it largely remains an unsolved problem based both on the limited understanding of biological vision and because of the complexity of vision perception in a dynamic and nearly infinitely varying physical world.

  • Natural Language Processing: It is a discipline that focuses on the interaction between data science and human language, and is scaling to lots of industries. Today NLP is booming thanks to the huge improvements in the access to data and the increase in computational power, which are allowing practitioners to achieve meaningful results in areas like healthcare, media, finance and human resources, among others.

  • Generative Adversarial Networks: Generative modeling is an unsupervised learning task in deep learning that involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset.

These are just a few of the many different fields-of-study in deep learning, at least the most common ones. The main context of this post is to introduce the best books about deep learning that can guide your progression in this field, it would simplify a lot of concepts and more important, the information would be easy to digest since it is coming from just one source. It is not an unknown truth that it can be really overwhelming when trying to learn a new skill online usually from different sources. I think that choosing and learning in sequence from an equipped book would be a very good way to start.

Top 5 Deep Learning Books in 2020 to learn Deep Learning


Deep Learning With Python

Summary:

Deep learning is the most interesting and powerful machine learning technique right now. Top deep learning libraries are available on the Python ecosystem like Theano and TensorFlow 2. Tap into their power in a few lines of code using Keras, the best-of-breed applied deep learning library.

In this mega Ebook is written in the friendly Machine Learning Mastery style that you’re used to, learn exactly how to get started and apply deep learning to your own machine learning projects. After purchasing you will get:

  • Read on all devices: English PDF format EBook, no DRM.
  • Tons of tutorials: 20 step-by-step lessons, 266 pages.
  • Projects: 8 end-to-end projects
  • Working code: 71 Python (.py) code files included.
  • Finally, Bring Deep Learning To Your Projects

Link: MachineLearningmstery

Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2

Summary:

Applied machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning.

Python Machine Learning, Third Edition is a comprehensive guide to machine learning and deep learning with Python. It acts as both a step-by-step tutorial, and a reference you’ll keep coming back to as you build your machine learning systems.

Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself.

Link: Amazon

Deep Learning (MIT Press Essential Knowledge series)

Summary:

An accessible introduction to the artificial intelligence technology that enables computer vision, speech recognition, machine translation, and driverless cars.

Kelleher explains that deep learning enables data-driven decisions by identifying and extracting patterns from large datasets; its ability to learn from complex data makes deep learning ideally suited to take advantage of the rapid growth in big data and computational power. Kelleher also explains some of the basic concepts in deep learning, presents a history of advances in the field, and discusses the current state of the art. He describes the most important deep learning architectures, including autoencoders, recurrent neural networks, and long short-term networks, as well as such recent developments as Generative Adversarial Networks and capsule networks. He also provides a comprehensive (and comprehensible) introduction to the two fundamental algorithms in deep learning: gradient descent and backpropagation. Finally, Kelleher considers the future of deep learning―major trends, possible developments, and significant challenges.

Link: Amazon

Deep Learning with TensorFlow 2 and Keras: Regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API

Summary:

Build machine and deep learning systems with the newly released TensorFlow 2 and Keras for the lab, production, and mobile devices

Deep Learning with TensorFlow 2 and Keras, Second Edition teaches neural networks and deep learning techniques alongside TensorFlow (TF) and Keras. You’ll learn how to write deep learning applications in the most powerful, popular, and scalable machine learning stack available. This book also introduces neural networks with TensorFlow, runs through the main applications (regression, ConvNets (CNNs), GANs, RNNs, NLP), covers two working example apps, and then dives into TF in production, TF mobile, and using TensorFlow with AutoML.

Link: Amazon

That’s it, the best 5 deep learning as of 2020. This list has been compiled based on reviews, price and I have had the chance to read a few of them myself. I hope these provides some assistance in your goal to learn and apply deep learning to real-world problems. Of course, it would take time, the time is relatively comparable to how much time is spent learning, practicing and building models.

What Next?

Now you’ve read some books hopefully, in reality you are yet to though. The truth is quite simple , reading is never the same thing as doing or practicing. Sure you are gonna get a lot of guidelines, understanding of deep learning from reading some of the best books around, but if your goal centers around becoming an expert in a field of deep learning, then you need to work with it every other day. I am not 100% qualified to give directions that I can guarantee would be perfect for everyone, because in a way, there is always a unique situation and way of doing things everyone has. The helpful thing for me is that I’ve passed through every single step myself and still doing. What I can say is this, as a beginner trying to have expertise in deep learning, the easiet way to progress is to specialize in one or two fields at first. How you can go about this, is finding that one area that interests you, it doesn’t have to be a huge interest at first, because interest and passion can grow as you practice deeper with it.

I took me time to discover what I loved best in the many branches of AI & DL. It can be a daunting process, daunting because you more than anything want to learn Deep Learning, but have no idea how to start. It can be very overwhelming if you try to have a go at “All” your areas of interest, because In truth, deep learning is fascinating - every part of it.

Here’s the action I hope you can take to guide your progress:

  • Start by Reading one of the recommended books, this would get you through the basics, concepts, branches of deep learning, some theories and even some practical approaches to deep learning.

  • Try to choose a field you want to start working in, but as much as this is an important step, it can also be helpful to dance around a bit, to find what you love best before making a choice - At the end of the day, regardless of what you choice is, be openminded in all cases. Now I would give an example of why I said so: My Interest in Deep learning is Computer Vision and Image Synthesis e.g Gans, at least that’s where my major interest lies. I avoided kaggle community because I thought most of the projects there were limited to “Data-Science and Machine learning”. Yh, I was quite ignorant and was strictly into Computer Vision. Short story, I decided to have a shot at kaggle, well, I found out that there were lots of computer vision projects available. And well, as a beginner, I completed some simple Data-science projects, got to learn pandas, scikit-learn and data-visualization libraries. This was great for me because I learnt some new stuffs and actually found out that I loved Visualizing data.

  • Well, the path to mastering Deep learning(deep learning might be too broad to master, let’s just say, your specific field) has many channels, one person can do so many stuffs along the way but get there later than someone who thoretically did less. My grammer isn’t too great here, I’m also growing in it just like you. What I can do though, is refer you to a great post by Jason Brownlee, in his post he talks about the Best way to Learn & Do Deep Learning - Everything in that post alings with my views. Deep learning Getting Started

Summary

In this article,

  • I shared with you some highly rated books on Deep Learning
  • We talked about Deep Leraning on the surface with some simplistic definitions
  • I listed a few popular fields in Deep learning (Computer Vision, NLP, Gans)
  • I highlighted some action steps you can take to start learning deep learning in practice

Thanks for reading through this post, I hope most that it would of some help to you. If you would like to ask about some more steps or anything at all , feel free to leave a comment below.