Inside Deep Learning Math, Algorithms, Models Using PyTorch with CoLab

This will my first in a series of computer book reviews using sample books from a site named manning.com. I am only a beginner, but I am learning a lot and want to share what I am learning. To begin with I am not a 'math' or 'computer' person, but I do understand the math vocabulary and the math symbols. As I stated I am only a beginner and always probably will be in learning about computer applications and programs.

I am finding this book somewhat understandable for even a beginner. Edward Raff teaches the steps to the program so that the reader can get a better grasp of the material. Edward also teaches the necessary vocabulary that goes with each program and as a refresher to the math skills that may be necessary.

Remember these are sample books and there are only selected chapters that the author is sharing. Chapter one starts out defining what Deep Learning is and it is in short neural networks or artificial neural networks that has lead to dramatic advances in the quality, accuracy, and usability of machine learning. Deep learning has a lot to do with our current living conditions like driving and living our lives by several means. The primary focus is mainly how to use and code these networks and to understand how and why they work at a deep level.

This chapter also goes on to define the term further in this way. It has to do with being a sub-domain of Machine learning which is also a part of artificial intelligence. It seems that deep learning is a way to make 'us' look smarter and make 'smart decisions'. Deep learning is a set of algorithms or 'building blocks' to help us solve our basic or any problems. It is also about how to sequence our ideas to AI (artificial intelligence). Learning is defined to machine language as deep learning is a mechanical process of getting the model to make the smart looking predictions on our data. It goes on to mention optimization or function minimalization. There is a block in yellow, I believe, all about the term 'backpropagation' about how many computers has started with this.

In starting to understand Deep Learning there will be some math for use for CoLab will be used along with Graphics Processing Units (GPU's), which is a requirement. Some basic Calculus and Statistics and Linear Algebra may be needed and reviewed. The basic building blocks will be 'Data as a Sequence'; 'Data as an Image' or 'Data as an Image (video)'. Chapter one then goes on to discuss 'tensors'. Deep learning frameworks do not use different classes or objects to distinguish between these many different types of data. Edward starts to use mathematical terms like matrices, vectors, and scalors which are tensors. He uses diagrams that are colorful and are easier to understand along with the explanations he writes.

There is another whole block of why do we care about GPU's which is a good touch to make understanding more clear along with his flowcharts which are also easy to follow. The reader will have an understanding of the math and the computer applications when reading his examples in gray. The exercises he has created at the end of each chapter will give practice to users. As I mentioned at the beginning of this article/review I am very much a beginner, but I did understand the math and basic computer vocabulary and with more practice I can use this program one day. Edward highlights throughout the book sections in gray what the computer screen should look like step by step if I read them right.

Remember this was only a sample of 'Inside Deep Learning Math, Algorithms, Models Using PyTorch with Google CoLab. You can go to manning.com if interested in reading this book in whole. There will be more of these lectures/reviews coming soon. The next one will be 'Principles of Cloud Design' written by David Clinton.

To be continued