Subscribe to DSC Newsletter

Why Deep Learning is Taking off? Season 1 : Part 1

First it was Machine Learning, and now all of a sudden Deep Learning is taking all the thunder even from Machine Learning. So what's the difference, and why all of a sudden Deep Learning has become the most buzzing new Technology of our Era? Is Deep Learning a false idol being Ubiquitously worshiped or is it the panacea which is going to take us to our Utopia?
Is Deep Learning a false idol being Ubiquitously worshiped or is it the panacea which is going to take us to our Utopia!
These are two extreme positions & the reality usually lies somewhere in between. To delve deeply on this question, we need to first know what Machine Learning & Deep Learning are, & the difference between the two.
Machine Learning, isn’t the name shouting it’s meaning itself?
The most important part of AI is to teach machines, so that machines then can do that work. Machine Learning is the discipline which devises the various processes to teach machines from Data, so that machines can learn, and then do what they are taught.
So it’s pretty to similar to how we teach humans?
No, in my experience Machines are far easier to teach LOL
When I tell people that I make machines smarter by teaching them, people think that I am on the border of lunacy & that’s effective what I do.
When I tell people that I make machines smarter by teaching them, people think that I am on the border of lunacy & that is effectively what I do
Machine Learning is about using algorithms like Linear Regression, Logistic Regression, Decision Trees & Support Vector Machines(to name a few) to teach machines using the Data.
Linear Regression, Logistic Regression, Decision Trees & Support Vector Machines
In any Machine Learning Application, Data is the only input which is split into two parts, one is called Training set and the other is called Test set. For the purpose of brevity, I am leaving Validation set out of the equation for now.
In any Machine Learning Application, Data is the only input
Training Data is used to train the Machine Learning Application.
Machine Learning algorithms are fed with data, and it gets trained. Once it’s trained on enough data, it’s accuracy is checked on Test set to find out how accurate the model is. Pretty good mechanism, is it?
So this is how companies like Netflix, Google, Amazon & Facebook are using their data to train Machine Learning Applications and make trillions of dollars.
Netflix, Google, Amazon & Facebook are using their data to train Machine Learning Applications & make trillions of dollar
This Post is a multiple part season like the ones you binge on Netflix & People have short attention spans so I will hold my thoughts on Deep Learning till the next post. With this, I rest.
The Question is "What do you Do with your DATA?" The answer to this question will decide the faith of your business in the next few years. So ask yourself " To be or not to be?" & Become the Hamlet of corporate world.

Views: 1668

Comment

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

Join Data Science Central

Comment by Leandro Seabra on August 25, 2017 at 4:19am

"People have short attention spans so..." Touchè.

Follow Us

Videos

  • Add Videos
  • View All

Resources

© 2017   Data Science Central   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service