God in the Machine: Westworld of HBO 2016

“These violent delights have violent ends

And in their triumph die, like fire and powder,

Which, as they kiss, consume.”

~William Shakespeare

Last week, I finished watching the amazing  TV series Westworld. As a Sci-Fi fan, I kindly tired of the repeated laser  gun and space ships,  this TV series is really an open-minded setup with a solid storyline of Artificial Intelligence (Hosts) and Human (Makers/Vistors).

Imagine that technology was so advanced, you could step into a wholly immersive virtual reality world that was very nearly as real as our own. A theme park, where you can live out your fantasies. No awkward headsets or VR to wear. No fuzzy graphics, keyboard, and mice. Because it’s all real—for the most part.

You can buy drinks at the local saloon, or pay for sex with one of the AI prostitutes at the bar. You can get in gun fights with outlaws, or save the town from murderous highwaymen. Or, if you really want to, you can go to a farm house, kill the elderly parents there and rape their daughter. This is where the stories are written, tinkered with, and the microcosm of Westworld manipulated for the entertainment of its guests.

Continue reading “God in the Machine: Westworld of HBO 2016”

Google open sources Embedding Projector to make high-dimensional data more manageable

Dear friends,  I’m sharing this great news that Google opens Embedding Projector for the world. Now everyone could enjoy the convenient approach to visualize high dimensional data on the web browser.

Based on my personal programming experience, t-SNE is a great method for high-dimensional data visualization, better than PCA on some data sets like MNIST.

You can download the Matlab Toolbox for Dimensionality Reduction; or download the t-SNE method for different platforms: t-SNE codes.

Moreover, check the following papers if you want to learn more  details about dimensionality reduction.

  • L.J.P. van der Maaten and G.E. Hinton. Visualizing High-Dimensional Data Using t-SNE. Journal of Machine Learning Research 9(Nov):2579-2605, 2008. PDF [Supplemental material] [Talk]
  • L.J.P. van der Maaten, E.O. Postma, and H.J. van den Herik. Dimensionality Reduction: A Comparative Review. Tilburg University Technical Report, TiCC-TR 2009-005, 2009. PDF

Here are the links for more information:

Continue reading “Google open sources Embedding Projector to make high-dimensional data more manageable”

Plan: Introduce the Softwares for Machine Learning

    Software List:  Matlab Basic Matlab  Advanced: LMS  Softmax SVM Neural Network Fizzy System ANFIS. Python Basic Python Advanced:   Numpy  Pandas Pandas  Matplotlib   Scikit-learn   The…

Source: Plan: Introduce the Softwares for Machine Learning

I am not sure when I could finish these, but I will try.

Open Courses, Free Softwares and Frameworks of Deep Learning

Just sharing my sources of Deep learning, if anyone finds this post helpful, please share it. The content will be updated with the new techniques and information.

Continue reading “Open Courses, Free Softwares and Frameworks of Deep Learning”

Andrew Ng just releases a free draft copy of his new book: Machine Learning Yearning – Technique Strategy for AI Engineers, In the Era of Deep Learning

machine_learning_yearning_v0-5_01_page_01
Cover of the Book

AI, Machine Learning and Deep Learning are transforming numerous industries. But building a machine learning system requires that you make practical decisions:

  • Should you collect more training data?
  • Should you use end-to-end deep learning?

  • How do you deal with your training set not matching your test set?

  • and many more.

Historically, the only way to learn how to make these “strategy” decisions has been a multi-year apprenticeship in a graduate program or company. I am writing a book to help you quickly gain this skill so that you can become better at building AI systems.

The book will be around 100 pages and contain many easy-to-read 1-2 page chapters. If you would like to receive a draft of each chapter as it is finished, please sign up for the mailing list.

Continue reading “Andrew Ng just releases a free draft copy of his new book: Machine Learning Yearning – Technique Strategy for AI Engineers, In the Era of Deep Learning”

How to start a science paper from a beginner

An article begins with the Title, Abstract, and Keywords.

The article text follows the IMRAD format, which responses to the question below:

  • Introduction: What did you/other do? Why did you do it?
  • Methods: How did you do it?
  • Results: What did you find?
  • And
  • Discussion: What does it all mean?

Continue reading “How to start a science paper from a beginner”

What soft skills do software developer need?

The biggest mistake that you can make is to believe that you are working for somebody else. Job security is gone. The driving force of a career must come from the individual. Remember: Jobs are owned by the company, you own your career!

— Earl Nightingale

Continue reading “What soft skills do software developer need?”

Should you ask a Question during Seminar?

Asking a question in a seminar is like a box of chocolates, you never know what you gonna get.

“All of the humanity’s problems stem from man’s inability to sit quietly in a room alone.”  

— Blaise Pascal, Pensées

The best thing to being Grad student is … “the free food” on a seminar.

Continue reading “Should you ask a Question during Seminar?”

Learning from data and Three learning principles

The learning problem and the principles before building a model.

This blog is mainly based on the book and lecture notes by Professor Yaser S. Abu-Mostafa from Caltech on Learning from data , you could benefit a lot from the lecture and videos.

Problem:

“In God we trust, and others bring data”.

If you show a picture to a three-year-old and ask if there is a tree in it, you will likely get the correct answer. But if you ask a thirty-year-old what the definition of a tree is, you will likely get an inconclusive answer.

We didn’t learn what a tree is by studying the mathematical definition of a tree. We learned it  by looking at trees. In other words, we learn from ‘Data’.

Continue reading “Learning from data and Three learning principles”