How Machine Learning Works, As Explained By Google

How Machine Learning Works, As Explained By Google

Confused about how machines teach themselves? Here's an overview on machine learning to help.  

Machine learning systems are made up of three major parts, which are:

1. Model: the system that makes predictions or identifications.
2. Parameters: the signals or factors used by the model to form its decisions.
3. Learner: the system that adjusts the parameters — and in turn the model — by looking at differences in predictions versus actual outcome.

Nov. 4, by Danny Sullivan is a Founding Editor of Marketing Land. He’s a widely cited authority on search engines and search marketing issues who has covered the space since 1996.

Machine Learning System :
Google’s Corrado stressed that a big part of most machine learning is a concept known as “gradient descent” or “gradient learning.” It means that the system makes those little adjustments over and over, until it gets things right.

Now let me translate that into a possible real world problem, based on something that was discussed yesterday by Greg Corrado, a senior research scientist with Google and cofounder of the company’s deep learning team.
Imagine that you’re a teacher. You want to identify the optimal amount of time students should study to get the best grade on a test. You turn to machine learning for a solution. Yes, this is overkill for this particular problem. But this is a very simplified illustration!