As deep learning and artificial intelligence slowly become last season, let’s revisit their predecessor, machine learning.
When my boy was ready to play with his blocks, I sat down and played around with it myself. He saw what I was doing and learned how to place each block and where. He learned and trained himself how to build his towers, barns, and space centers
Machine learning is a set of computer programs or algorithms that uses data to train itself so that it need not be explicitly programmed to do each and every function all the time. It uses the existing data to gain insights and behaves accordingly. This new insights become fodder for similar functions along with more data next time
As much as machine learning is associated to algorithms, it is also strongly associated with advanced Statistics. On a very high level, in machine learning write programs to fit a model on the data.
The degree to which this fitting is done can be different for different functions like there are methods like reinforcement learning that do not use any pre-existing data. Also, in machine learning, the number of variables we use for modeling can range to hundreds of millions, thereby scaling up the statistical models to levels beyond imagination.
Did I persuade you into learning this very interesting field yet or should I talk more? Coursera offers a free course by the machine learning connoisseur Andrew Ng (Co-Founder of Coursera as well) himself that you absolutely need to check out. You can find it here.
If I didn’t persuade you yet, I would take you to Andrew Ng’s Twitter handle @AndrewYNg and you are essentially trapped. Your journey along the machine path has officially begun!
E-mail us at she@shedrivesdata.com to inspire our readers with your story – be it your success story or a lesson learned, share what you learned or send some love to a friend. We would love to hear from you!