Start reading Understanding Neural Networks on your Kindle in under a minute. Don't have a Kindle? Get your Kindle here.
Programming Books C Java PHP Python Learn more Browse Programming Books

Deliver to your Kindle or other device

Enter a promotion code
or gift card
 
 
 

Try it free

Sample the beginning of this book for free

Deliver to your Kindle or other device

Anybody can read Kindle books—even without a Kindle device—with the FREE Kindle app for smartphones, tablets and computers.
Sorry, this item is not available in
Image not available for
Color:
Image not available

To view this video download Flash Player

 

Understanding Neural Networks [Kindle Edition]

John Iovine
3.1 out of 5 stars  See all reviews (10 customer reviews)

Print List Price: $14.95
Kindle Price: $2.99
You Save: $11.96 (80%)

Formats

Amazon Price New from Used from
Kindle Edition $2.99  
Paperback $12.89  
Shop the new tech.book(store)
New! Introducing the tech.book(store), a hub for Software Developers and Architects, Networking Administrators, TPMs, and other technology professionals to find highly-rated and highly-relevant career resources. Shop books on programming and big data, or read this week's blog posts by authors and thought-leaders in the tech industry. > Shop now

Book Description

Understanding Neural Networks The Experimenter's Guide is an introductory text to artificial neural networks. The book begins with examining biological neurons in the human brain and defining their real world mathematical and electronic equivalent.
Building upon this foundation the book contains hardware and software projects that illustrate neural networks. Hardware projects include a op-amp neuron that tracks a light source, speech recognition system, and machine vision system.
Software projects include a Perceptron program and Back-Propagation networks.
This book provides a comprehensive introduction to neural networks.

Customers Who Bought This Item Also Bought


Product Details

  • File Size: 1784 KB
  • Print Length: 166 pages
  • Simultaneous Device Usage: Unlimited
  • Publisher: Images Publishing; 2 edition (September 5, 2012)
  • Sold by: Amazon Digital Services, Inc.
  • Language: English
  • ASIN: B0096U45RY
  • Text-to-Speech: Enabled
  • X-Ray:
  • Lending: Enabled
  • Amazon Best Sellers Rank: #302,039 Paid in Kindle Store (See Top 100 Paid in Kindle Store)
  •  Would you like to give feedback on images?


Customer Reviews

Most Helpful Customer Reviews
14 of 16 people found the following review helpful
Format:Kindle Edition|Verified Purchase
The book contains very basic, egregious mistakes. For example, in one place the author writes "Homonyms are words that sound alike. For instance, the words cat, bat, sat and fat sound alike." No! Homonyms are, in short, words that are pronounced exactly the same but have different meanings. Those words listed as examples may rhyme, and those words may sound confusing to speech-recognition systems, but those words are most definitely not homonyms!

So perhaps this glaring mistake can be ignored because this is a book about neural networks and not one about grammar? Perhaps... but if the author can't be bothered to properly research the definitions of basic terminology, would you trust him to properly research more advanced concepts?

If you said "no," you are probably right. As just one example, later in the book the author goes on to claim "Hopfield networks are capable of solving mathematical problems deemed impossible for a computer to solve, like the travelling salesman problem." No! First of all, the travelling salesman problem is an example of an NP-hard problem, which means that it takes a long, long time for computers to solve problems like these, not that it is impossible to do so. Second of all, anything possible with Hopfield networks is of course possible on computers, since Hopfield networks run on computers. The author probably meant "rule-based systems" instead of "computers," but still, sloppy use of language. Finally, that sentence is outright incorrect, because if Hopfield networks are indeed able to offer optimal solutions to the travelling salesman problem in less than exponential time, then P = NP would effectively be proved, and thus far that famous problem is still unsolved.
Read more ›
Was this review helpful to you?
3 of 3 people found the following review helpful
5.0 out of 5 stars Good book on neural networks September 13, 2013
Format:Kindle Edition|Verified Purchase
I almost didn't purchase this book based on the two negative reviews, but considering what I was able to read in the sample chapters and the price I decided to purchase it anyway. I'm glad I did. The comments made by Bob Jones regarding the usage of the word homonym and the traveling salesman issue must be from an earlier edition. The errors he pointed to do not exist in my edition.

This book doesn't promote itself to be a college textbook on artificial neural networks, but an introduction to neural networks and how they function for the average or lay person. In this regard it is excellent. If you're looking for a textbook, by all means buy a textbook, this is not your book.

The added value is of course the electronic experiments. One experiment shows you how to turn an op-amp into an electronic neuron and have it track a light source. Now another reviewer complained about the op-amp neuron. To him/her I say the feedback loop is the person adjusting the potentiometer for proper light tracking operation. It's not automatic. The person is the trainer and/or feedback loop. In addition I remember seeing this experiment in Scientific American magazine Amateur Scientist column on how to build an electronic neuron. When I checked, the article was written by the same author. If Scientific American says its an electronic neuron then I'll take Scientific American's word for it rather than two no name reviewers without any credentials.

I believe this book deserves four stars, some of the information is dated, but I'm giving it five stars to compensate for the other two negative dumb dumb reviews.
Comment | 
Was this review helpful to you?
1 of 1 people found the following review helpful
5.0 out of 5 stars Great book! I had lots of fun reading this one. October 21, 2013
Format:Paperback|Verified Purchase
This is a really good read. I was an engineer from the 60's on and was very excited about all the early work in neural networks, fractals, chaos, etc. BUT I was too busy pursuing a creer and supporting my family to branch off into this field. Now I am retired and am just starting to re-discover some of these fun things. I recommend this book. My only confusion is with his matrix multiplacation on page 131 . . I may be wrong - or the presentation may be lacking - but he appears to be multiplying matricies that can't be multiplied. Would love to hear from others who were confused by this or can explain it to me. Email me at rmckeon4@cableone.net
Rick
Comment | 
Was this review helpful to you?
1 of 1 people found the following review helpful
4.0 out of 5 stars Very good overview of neural nets July 24, 2013
Format:Kindle Edition|Verified Purchase
I liked it. The author clearly is very well informed about neural networks and does a good job of explaining what makes them tick. Only reason I did not give it 5 stars was because I think it was a bit too much hardware neural network chapters but that just my personal thought.
Comment | 
Was this review helpful to you?
3 of 4 people found the following review helpful
1.0 out of 5 stars Disappointing June 26, 2013
By uslex
Format:Paperback|Verified Purchase
I have to agree with the reviewer Bob Jones. I also have to confess, I purchased the book even after reading his one-star review. I am an electronics hobbyist and I was intrigued at the prospect of building a neural network from hardware components rather than programming one. If that is your desire, this book will disappoint. The author demonstrates an op amp servo controller and calls it a neuron. It has no feedback loop to enable training. You simply manually adjust the variable resistors to produce the desired output. Other projects in the book are just simple hardware kits like you might buy at Radio Shack. For one of the projects the author even admits that he does not know if the chip uses a hardware implemented neural network or not. He says that, from the description of the chip, "it sounds neural to me"! Really??? His programming examples are in QBasic - not a programming language you probably use, or want to learn to use. Bottom line, the book is superficial, riddled with errors, and unsatisfying from either a software or hardware point of view.
Was this review helpful to you?
Most Recent Customer Reviews
Search Customer Reviews
Only search this product's reviews

What Other Items Do Customers Buy After Viewing This Item?



Forums

There are no discussions about this product yet.
Be the first to discuss this product with the community.
Start a new discussion
Topic:
First post:
Prompts for sign-in
 


Look for Similar Items by Category


ARRAY(0xa571d1f8)