Singapore International Science Challenge (Machine Learning Challenge)

SISC 2017 Background Image

Machine Learning Challenge

In recent years, the fields of artificial intelligence and machine learning have seen significant growth, especially in terms of accessibility. This is primarily driven by the need to autonomously process and analyse increasing amounts of data, both in terms of volume and dimension, so as to deliver more dynamic and thus richer solutions.

The current iteration of SISC seeks to harnesses this increased accessibility to machine learning in order to challenge students to learn and apply machine learning.

In order to better prepare for the Machine Learning Challenge, participants are encouraged to review the following introductory material.

An Introduction to Machine Learning

There are a myriad of material that can be found online on Machine Learning. However, as a general introduction, please refer to the article: How to Get Started as a Developer in AI on Intel’s Developer Zone.

Intel’s Software Developer Zone on Machine learning also includes many other resources on Machine Learning.

For a more detailed treatise, please refer to the following papers:

For even more detail into the subject, the following text is recommended:

Machine-learning-book

Machine Learning (Mitchell, 1997)

You can also learn by reviewing the following (free) online courses:

MIT-300x244

MIT Open Courseware Course

Open-classroom-300x198

Stanford Open Classroom Course

udacity-300x127

Udacity Course

Developing Machine Learning Solutions using Python

To develop machine learning solutions, and more specifically, to complete the SISC machine learning challenge, all participants should be familiar with the Pythonprogramming language, and the scikit-learn module.

To learn more about Python, there are many resources available:

  • Online Courses

o    The LearnPython.org interactive Python tutorial

o    Programming with Python by the Software Carpentry Foundation

  • Tutorials

o    The Python Tutorial from the official Python 3.6.1 documentation

  • Textbooks

How-to-think-like-a-scientist

How to Think Like a Computer Scientist: Learning with Python 3 (Wentworth et al., 2017)

A-bit-of-pythons

A Byte of Python (Swaroop, 2013)

And on the scikit-learn module, please refer to the scikit-tutorials. Since you will be expected to utilise these libraries for the 2017 SISC Machine Learning Challenge, it is strongly advisable that you comprehensively review the scikit-learn tutorials and documentation.

More Specifics about the Actual Challenge

Details of the actual challenge will only be made available to SISC participants on the 28th of June.