Deep Learning vs Machine Learning vs Pattern Recognition

I think I have a pretty good grasp on the meaning and scope of 'Machine Learning' but less so on the emerging field of 'Deep Learning'. Tomasz Malisiewicz has both the background and perspective to put these terms in context for us and I enjoyed his clear explanation. You can see it here:

Lets take a close look at three related terms (Deep Learning vs Machine Learning vs Pattern Recognition), and see how they relate to some of the hottest tech-themes in 2015 (namely Robotics and Artificial Intelligence). In our short journey through jargon, you should acquire a better understanding of how computer vision fits in, as well as gain an intuitive feel for how the machine learning zeitgeist has slowly evolved over time.

Putting a human inside a computer is not artificial intelligence.

2 members like this

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Sione Palu on August 4, 2015 at 7:17am: Relevant:

"A Common Logic to Seeing Cats and Cosmos"

https://www.quantamagazine.org/20141204-a-common-logic-to-seeing-ca...

Comment by Sione Palu on August 3, 2015 at 3:12pm: Function Compositional Mapping:

https://en.wikipedia.org/wiki/Function_composition

In Electrical/Electronic Engineering, they don't call it learning. They call it System Identification. In machine learning they call it learning. Different terminologies from different domains & yet they mean the same thing mathematically and that is functional mapping.

Comment by Sione Palu on August 3, 2015 at 3:07pm: In mathematical terminology they all lumped into functional mapping, whether its machine learning, deep learning, pattern recognition, system-identifications, etc, etc.

One maps X into Y via an approximating functional mapping function f , ie, Y:--> f(X)

Too many throw around terminologies these days without practitioners understanding of what they mean.