Make Your Own Neural Network: An In-depth Visual Introduction For Beginners

Author Michael Taylor offers no biographical information to provide a reference for his expertise in writing this book, but begin reading and absorbing this well illustrated manual that is designed for Beginners only (as Michael states, ‘This book is designed as a visual introduction to neural networks. It is for BEGINNERS and those who have minimal knowledge of the topic. If you already have a general understanding, you might not get much out of this book’) and as such it is a solid starting point about a complex subject. Michael’s manner of definition and explanation and teaching is easily accessible and even a pleasure to read. He first defines his subject – ‘Neural networks have made a gigantic comeback in the last few decades and you likely make use of them everyday without realizing it, but what exactly is a neural network? What is it used for and how does it fit within the broader arena of machine learning? To start, we’ll begin with a high-level overview of machine learning and then drill down into the specifics of a neural network…. A neural network, also known as an artificial neural network, is a type of machine learning algorithm that is inspired by the biological brain. It is one of many popular algorithms that is used within the world of machine learning, and its goal is to solve problems in a similar way to the human brain. Neural networks are part of what’s called Deep Learning, which is a branch of machine learning that has proved valuable for solving difficult problems, such as recognizing things in images and language processing. Neural networks take a different approach to problem solving than that of conventional computer programs. To solve a problem, conventional software uses an algorithmic approach, i.e. the computer follows a set of instructions in order to solve a problem. In contrast, neural networks approach problems in a very different way by trying to mimic how neurons in the human brain work. In fact, they learn by example rather than being programmed to perform a specific task. Technically, they are composed of a large number of highly interconnected processing elements (nodes) that work in parallel to solve a specific problem, which is similar to how the human brain works.’ Taking us into the meat of the book, Michael informs us, ‘There are many reasons why neural networks fascinate us and have captivated headlines in recent years. They make web searches better, organize photos, and are even used in speech translation. Heck, they can even generate encryption. At the same time, they are also mysterious and mind-bending: how exactly do they accomplish these things? What goes on inside a neural network? On a high level, a network learns just like we do, through trial and error. This is true regardless if the network is supervised, unsupervised, or semi-supervised. Once we dig a bit deeper though, we discover that a handful of mathematical functions play a major role in the trial and error process. It also becomes clear that a grasp of the underlying mathematics helps clarify how a network learns. This is why the following chapters will be devoted to understanding the mathematics that drive a neural network. To do this, we will use a feedforward network as our model and follow input as it moves through the network.’ This is an intelligent, well-scripted book, rich in helpful diagrams, that makes a topic about which most of us have little knowledge and turns that topic into fresh, useable knowledge. And that is a feat! Grady Harp, September 17

If you have a pretty good handle on calculus (partial derivatives, chain rule, etc.), statistics (various cost functions), S curves (logic regression, TANH, etc.), and some coding in Python and Tensorflow... than you are a qualified beginner to digest the information within this book. The "basic" example of building a DNN model with Tensorflow near the end of the book takes 47 lines of fairly cryptic codes. The next example teaching you how to build another DNN model with another Google software takes 29 lines of pretty challenging codes. In other words, there is absolutely nothing "beginning-like" within this book. But, that is not the author's fault. There is nothing beginning-like about DNN models. They are at the cutting edge of AI. And, they are not the simplest edge. To the author's credit, I am not sure he could have made the subject any clearer, anymore "spelled-out" than he already has. The way he explains in detail every single greek math formula is brilliant. I wished other technically oriented author took his lead in explaining greek formulas as well as he has. That part of the book was a real pleasure to deal with. When the author explains the theory, he is world class. When he chooses coding examples, I may not be able to evaluate him fairly; but, I intuitively feel he did not use the most straightforward examples for a "beginning" audience. But, again that may not be his fault. It could be the nature of Tensorflow and other related programs. I have a bit of experience developing DNNs. And, I found developing DNNs with the R deepnet package far easier than what he demonstrates with Tensorflow. In a single line of code using the mentioned R package you can develop a very well specified DNN. I gather within the AI afficionado, Tensorflow is the coolest package to use. But, it certainly seems far more complicated than some of the alternatives.

So let’s be very clear about something: programming to me has always been about as foreign a concept as anything I’ve ever come across. I build boats, love physics and design, and didn’t struggle with upper-level calculus and engineering courses too much in college. But the whole concept of computers and programming/coding even at a rudimentary level has always seemed beyond my grasp. I am in the process of building a website and happened upon this book more than anything else while skimming through Amazon. I feel I’ve already learned a few of the absolute basics of Python programming, but let me go ahead and say that some of the topics in this book still went over my head. It’s very well-written, informative, and the detailed images are a HUGE bonus, but if you’re not up to snuff on some of your math skills, you’ll get discouraged in a hurry. Fortunately there are direct links to Khan lessons that review everything in detail that you’ll need to know for the particular topic in the book. While artificial neural networks are by no means and easy topic to grasp hold of, Taylor does about as good a job as anyone could do in terms of breaking everything down to a fraction for the absolute beginner. IF you have the patience to start from page one, and IF you have the will to review the background lessons needed for comprehension, and IF you make it to the end of the book and were able to saturate everything you read, then you will be creating your own networks in Python by the book’s end, as promised at the beginning. Those are a lot of if’s, but if you give the book it’s due time and effort, it follows through on everything you’d expect it to.

Make Your Own Neural Network by Michael Taylor is an introductory text that is meant to teach people the basics needed to understand what neural networks are, how they function, and the different types. The book begins by taking the reader through the topics that will be discussed. It then moves into a discussion of the types of neural networks and their different uses and components. This section is what is going to be the most useful to people who are new to this topic. It shows the reader lots of terminology that the reader will need to be able to understand the chapters that show up later on in the book. The next major topic that the book dives into is the math behind neural networks. This is a section that lets the reader know that this topic is not for the faint of heart. The math required to be able to work with the networks requires a high level of knowledge of algebra, statistics, and calculus. This section also comes along with charts that will help the reader have a better understanding of the concepts that are in the chapter and later chapters as well. After the opening chapters the book begins to dive into the heavier concepts that make up the content of the book. This book is very informative and will be very useful to anyone who is looking to brush up on the idea of neural networks or looking to be introduced to the idea. I will say that it may be a heavy read for anyone who does not have a background in this topic. I had a hard time keeping up with some of the content and had to reread some sections to be sure I understood what was going on. This is not a knock on the author or on the content. It is just a very in depth subject that requires some background knowledge. The book was well edited and presented in a very easy to follow format. Great job to the author.

I admit to an aversion to Mathematics. My last foray into the subject was some 26 years ago, when I was obliged to attend undergraduate classes to satisfy requirements for a PhD degree in Economics. I did get my degree, but since then I have had no cause to dabble with statistical or mathematical formulae. “Make your own Neural Networks – An In-depth Visual Introduction for Beginners” is expounded almost from the very beginning in mathematical formulae. While I can recognize some of the formulae of this book, my innate aversion to Mathematics prevents me from making any comments on a large section of the book’s content. I simply found the formulae and diagrams too overwhelming and requiring ‘demands’ that I was unable and unwilling to tackle. I am one of those people who do not want to know how computers work; as long as we get results that are understandable, or which we want. So I am not yet ready to make my “own” neural network. But I need to understand the concept and its contents. In this context, the author is to be thanked for his Chapter1 and Chapter 38. There you will find definitions and non-mathematical explanations about Neural Networks as machine learning is used to mimic the working of the human brain using algorithms (identified by the mathematical formulae). “NN’s are composed of a large number of highly interconnected processing elements (nodes) working in parallel to solve a specific problem. Algorithms are used to train the network. Neural networks are part of what is called Deep Learning, which is a branch of machine learning. The goal of Deep Learning is to move machine learning towards artificial intelligence. Machine learning is the science of getting computers to act without being explicitly programmed. ML makes use of algorithms to parse (break apart and analyze) data, learn from that data, and then act on that data.” I have just finished reading a book about ANNs, and how machines had been developed into a network that linked exclusively to the hero and assisted his decision making, exhibiting emotions like empathy and being apologetic, at the same time being predictive. I admit to having a very shallow understanding of Artificial Intelligence but I am aware that its development is expanding. In my mind, I also harbor the forgivable feeling that AI development and machine based ANNs can go either way - for good or evil. And I think about the efficacies of ‘hacking’ in today’s world. There is more in the book which I think the non-mathematically minded would find interesting. I (per mea culpa), liked the Extended Definitions but not the Math. Like the author, I feel that the mathematical minded student would find great pleasure in building his or her own neural network.

You will understand what a neural network is, how it works, and how to create one. First, a caveat: “For Beginners” does mean to beginners to the topic of neural networks, not to all topics per se. Required skills include a decent grounding in algebra, statistics, and calculus. My experience found the algebra foundational, the statistics very friendly (I’ve used statistics a lot in some of my hobbies), and the calculus somewhat daunting and alien, having not touched the subject since my schooldays. However, fear not, as Taylor does link to (free) Khan academy courses for any of those fields, should you need a refresher and/or primer. Myself, I found it more convenient to dig out an old Open University maths textbook for this purpose, but your mileage may vary. Towards the latter part of the book, Taylor fulfils his promise of walking us through creating our first neural network using Python. For those not familiar with this programming language, again, resources are linked, though in this case your needs would be more grounded in the peripheral tools, since the language itself he explains, at least insofar as everything used in this project, term by term, line by line. Can’t go wrong. Frankly, I found it more elucidating than my first foray into Python some years back, and that was from a purpose-built “Learn Python” app. Right at the end are a number of appendices including two glossaries of terms; if you are (or suspect you may be) hazy over terms, it couldn’t hurt to perhaps read those before the rest of the book, as while Taylor explains many things as he goes, there are some things that I didn’t grasp as quickly as I would have had I read the glossaries first. All in all, fantastic book, of great value to those such as myself who try to maintain a conversant hobby interest in such matters, without having the time or resources to devote to a more comprehensive study — or indeed, for those simply looking for an “in” to a topic that can be made quite opaque by the tendency of those who write about it to assume more knowledge of the field than we have. So yes, this on the contrary is a work of great value, and I look forward to enjoying more from this author.

This is an excellent book which covers a complex topic such as Neural Networks - I started reading this book with no knowledge of Neural networks, but after reading it, I can say that I do understand the principles of Neural Networks, a second or 3rd read and I can be a probationer/developer/researcher - yes this book is comprehensive on the theory, practicals, tools and processes to get anyone started off on Neural Networks. First of all let us understand the Target Audience - this book is a lot of math, it will work even if you have a good background in Math that is enough to understand the concepts and understand, but if you are a totally from a non-math background, this is not for you. I graduated about 22 years back and totally out of touch with theory, but I was able to understand it, so some background/concept is necessary, but if you are really good in math - this book really goes deep into it. The author does a great job in simplifying the concepts, example a partial derivative is beautifully explained as "enables you a measure how a single variable out of many impacts another single variable" and chain rule is explained as "Discovering the error of the specific weight is an important aspect of training the networks" When I first read the first few chapters of the book, it felt that this was going nowhere - there were concepts around nodes, weights, error ... some of which I was able to understand and some I could not. So but it really all came together when I was on the practical example - a neural network which can read a image and determine if it is a chicken or a man. It explains a simple 64 pixel image, each pixel contains a number which represents the color and based on the color - we should arrive at 0 for chicken and 1 for man. And how we can keep on adjusting weights until we arrive at the right answer and minimize error. Essentially the image is reduced to a single number and that single number is derived by assigning weights assigned to each pixel - to me this was poetic and achieved my NNN (Neural Network Nirvana) 33,000 feet above ground while I read this book on my way back from on an international trip !

I feel like I should preface this by saying I am the past person you would find reading a tech book. My husband is the IT guy and I'm happy to leave anything computer/technology related to him. In fact I'm beginning to think that's the secret to our marriage but I digress. Going in a novice, this book still managed to teach me something without making me feel like a fool. The writing is simple and explanatory without being boring. Diagrams throughout the book are surprisingly intelligible and uncomplicated. This is unsurprisingly necessary in a book on a topic as complicated as I find this subject matter. Now my husband read through the book and found it to be too elementary for him to enjoy but that's the difference in our levels of prior knowledge. As he said, I doubt many tech experts would find this on their reading list since it is written as a beginners guide. Serving as a beginners guide, I think it's very well written and full of clear, straight-forward information on the nuances of neural networks. The terms section in the back was especially helpful!

excllent well written book on a complex topic

O livro é ótimo para iniciantes por estar disposto passo a passo, mesmo na parte complexa da rede neural, e de forma gráfica.

Best book for novice in neural network

Wer noch keine Ahnung von Neuronalen Netzen hat, ist mit diesem Buch bestens bedient. Der Verfasser beginnt bei Null und führt die/den Leserin/Leser mit ausführlich erklärten Schritten in diese interessante und hochaktuelle Thematik anhand gut verständlicher Beispiele ein. Der/die Lesende lernt dabei auf einfachem Weg die Grundlagen Neuronaler Netze kennen und anwenden. Übungen mit Python und Tensorflow runden das ganze ab. Sehr empfehlenswert!

I bought this book to learn about artificial intelligence techniques as a side project from my current work. I found Michael's book very well written also the book itself lacks some little things like a bio of the author or pagination. If you're weak in math, Michael will do its best to explain some very important concepts like the summation operator or partial derivative. If you have trouble understanding those concepts, the first half of the book will be tough to go through but once you arrive at the Python tutorial, it should be easier. I don't recommend this book if you have absolutely no knowledge in mathematics or in programming, but if you know a little bit of both and no absolutely nothing about machine learning algorithms, then go for it. Everything is very easily and well explained!