Monday, May 22, 2017

Flash sale: OpenCV with Python Blueprints for only $10

For a limited time only, you can get OpenCV with Python Blueprints and any other eBook or video for only $10 on the Packt website. That's a staggering 77% discount! The flash sale will be going on for only a few days, so if you've been toying with the idea of getting some of these books, make sure to act now.

Michael Beyeler
OpenCV with Python Blueprints
Design and develop advanced computer vision projects using OpenCV with Python

Packt Publishing Ltd., London, England
Paperback: 230 pages
ISBN 978-178528269-0
[GitHub] [Discussion Group] [Free Sample]

Sunday, May 14, 2017

Highlights and new discoveries in Neuroscience (April 2017)

In the latest edition of this monthly digest series you can learn how your brain activity changes under the influence of psychedelic drugs, why brain games won't actually make you smarter, and how gene therapy might be able to treat patients blinded from retinitis pigmentosa.

Tuesday, April 25, 2017

Pre-order now: Machine Learning for OpenCV

You might be wondering what I have been up to, since my blog has been quiet for a while. Don't worry, I'm still here!

Truth is, in the little spare time I seem to have these days, I've been working on a new book: Machine Learning for OpenCV, coming out later this year! You can pre-order it on the official website of Packt Publishing Ltd. or Amazon.

This will be an introductory book for folks who are already familiar with OpenCV, but now want to dive into the world of machine learning. The goal is to illustrate the fundamental machine learning concepts using practical, hands-on examples. As always, all source code will be available for free on GitHub.

The outline of the book is as follows:

  1. A Gentle Introduction to Machine Learning
  2. Working with Data Using OpenCV and Python
  3. First Steps in Supervised Learning
  4. Representing Data and Engineering Features
  5. Using Decision Trees to Make a Medical Diagnosis
  6. Detecting Pedestrians with Support Vector Machines
  7. Implementing a Spam Filter with Bayesian Learning
  8. Discovering Hidden Structures with Unsupervised Learning
  9. Using Deep Learning to Classify Handwritten Digits
  10. Combining Different Algorithms into an Ensemble
  11. Selecting the Right model with Hyper-Parameter Tuning
  12. Conclusion

Stay tuned for more details!

Saturday, February 25, 2017

How to choose the right algorithm for your machine learning problem

With the recent machine learning boom, more and more algorithms have become available that perform exceptionally well on a number of tasks. But knowing beforehand which algorithm will perform best on your specific problem is often not possible. If you had infinite time at your disposal, you could just go through all of them and try them out. The following post shows you a better way to do this, step by step, by relying on known techniques from model selection and hyper-parameter tuning.

Sunday, February 19, 2017

Highlights and new discoveries in Computer Vision, Machine Learning, and AI (January 2017)

In the latest issue of this monthly digest series you can learn what happened at CES 2017, what's new in the world of self-driving cars, and how Intel got all these drones up in the sky during the Super Bowl's Halftime Show.