Top Selected Products and Reviews
-
1.
- In Stock.
List Price: $80.00 Price: $49.97 You Save: $30.03 (38%) "Very good book, likely to be heavily cited in future ..." - By Jeffrey Heaton (St. Louis, MO)
This will very likely become "the textbook" of choice for graduate level neural network classes looking for a broad mathematical foundation for deep learning. This is very important, as there have been a number of important technologies introduced that make classical neural networks into what we think of today as "deep learning". The book is divided into 3 highly effective thirds. The first third provides a mathematical background and can be skipped by those who already understand linear algebra, probability and calculus at a high enough level for the book. The 2nd third introduces what we think of in 2016 (and beyond) as deep learning. The final third introduces the most current research that might likely become part of the mainstream of deep learning. Those looking to implement current deep learning (and not research) can safely skip the last third. Skipping the middle ... full review(162) -
2.
- In Stock.
List Price: $49.99 Price: $33.85 You Save: $16.14 (32%) "Quality book" - By Dimitri Shvorob
"Real-World Machine Learning" was the antidote after going through a couple of ugly, half-baked and semi-competent "book products" from Packt. It is uplifting to see an original, expert, well-written and visually attractive book.
Trying to describe it, I would note three things that the book is not. It is not obviously more "real world" than its competitors: the "real world" reference seems to be a forgivable differentiation exercise. It is not thick: 230 pages. It is not a textbook or a catalogue of machine-learning algorithms - which you will need to get. (I would suggest "Introduction to statistical learning" by James, Witten, Hastie and Tibshirani). It is, however, a thoughtful introduction to and overview of machine-learning methods, appropriately remembering about the context and life-cycle of an ML project, and keeping things hands-on with small Python examples, but managing not to fall into the catalogue mode.
I have ... full review(8) -
3.
- Available for download now.
Price: $2.99 "Excellently articulated review of random forest basics" - By Michael Reca
For anyone completely new to the idea of random forests, I would highly recommend this book. It goes into sufficient mathematical detail about the different facets of the algorithm without getting lost in those details. I feel this was a wonderful introduction to random forests for me.(125) -
4.
- In Stock.
List Price: $44.99 Price: $24.00 You Save: $20.99 (47%) "I decided on this book because of all the other good reviews. I have since picked up a few ..." - By Michael E
I'm a senior undergraduate student in electrical and computer engineering, and decided to make use of machine learning for my senior design project. Having had some experience in python (but not much with matplotlib or scipy), I decided on this book because of all the other good reviews. I have since picked up a few other books related to machine learning, but none can even compare to this. It's stellar! In three weeks I have managed to give myself a comprehensive crash course in classification algorithms using Python which is enough to give me a rolling start on my design project. I am about half way through the book, and apart from very few minor errors (to be expected in a first edition book), I cannot find any faults in it. It's a great resource for someone who wants to learn about machine learning but doesn't know where to start. ... full review(119) -
5.
- In Stock.
List Price: $105.00 Price: $92.89 You Save: $12.11 (12%) "Excellent book with a question" - By Mike MOrgan
It is an excellent book, ideal for my work and, I imagine, for many others in need of advancement into machine learning from the various fields of statistics. The only thing is, there is an equation I believe is incorrect, and it turns out to be one I really need to understand. I have the fifth printing, and it is on page 118, section 4.3.3, equation number (4.91). I have written to the suggested email for Kevin Murphy a couple of times, asking if the equation says what it means, or if it might be some kind of error. Have not heard back, but perhaps I will soon. This is a great book, which may surprise people who are not "just at" the level of training needed to follow the development. But the target audience is, I think quite large and in need of ... full review(89) -
6.
- In Stock.
List Price: $15.95 Price: $12.76 You Save: $3.19 (20%) "A good place to start" - By William H. Panning (Prospect, KY USA)
Deliberately written for the non-specialist, Alpaydin's book provide a deliberately high-level summary of the main areas and specialties in machine learning. It is non-technical, and therefore ideal for the corporate executive or undergraduate student. For the non-specialist, it is a good starting point for a long road, and has adequate references to follow-up resources. Written by one of the luminaries in the field.(39) -
7.
Practical Machine Learning with H2O: Powerful, Scalable Techniques for Deep Learning and AIby Darren Cook- In Stock.
List Price: $39.99 Price: $25.52 You Save: $14.47 (36%) "great machine learning book" - By manuel
This book is an ample introduction of H2O for R and Python practitioners. Those interested in state-of-the-art machine learning and deep learning approaches will enjoy this book completely, whether they are beginners or proficient R and Python users for statistical analysis. The author makes clear descriptions and his explanations are always accessible. His high-quality sense of humour interspersed throughout the text helps maintain the interest in the text as one reads. I would love to read more of this author.(7) -
8.
- In Stock.
Price: $37.77 "An excellent guide" - By Geoff
I actually really love this book. The quality of the grammar and spelling throughout is very poor (the book reads like it was written by a ten-year old) yet in many ways this is its greatest strength. Anyone who was given up on learning guides because the language and technical jargon used is unfathomable need not worry at all here. The writing is so straightforward that it makes learning the models a breeze.
My only criticism is that the book contains a lot of diagrams which were produced in R with no mention of the code that produced them, which is silly because in many cases its a one liner. It means you have to dig around on the internet to find out how to do it.
Overall though this is great and I find myself strangely compelled to read the author's other books.(12) -
9.
"3 for Content 5 for author’s support" - By Abacus
The book is reasonably good. It explains Deep Learning fairly well in a manner that is digestible for the non-PhD (notice the topic is very technical by nature, so it does cater to an audience that has a good understanding of quantitative methods in general). A definite positive associated with this book is that the author gives you exposure and teaches you how to use three different R Deep Learning packages.
However, the narrative includes a few confusing statements. For instance, the author advances that Deep Neural Networks (DNNs) are the equivalent of a series of Log-linear regression models. That’s inaccurate. He meant to say Logit Regression models instead. Also, throughout the book he repeats that it is critical to standardize or scale the variables (using a Min/Max scaling) so as to render them Normally distributed. However, those procedures will not change ... full review(2)
