Artificial intelligence is a paragliding term, and things can get confusing when we start moving down the specificity chain - especially when the names are so similar, e.g. deep learning vs. machine learning.

Let's make that distinction between deep learning versus machine learning; they're related quite closely.

Machine learning is the wider category here, so let's first define that.

Machine learning is an AI field in which the program "Learns" through data.

That learning data could come from a large set labeled by humans - called ground-based truth - or the AI itself can generate that.

In order to train a machine learning algorithm to know what a cat is - you knew the cat was coming - or you could not feed it with an immense collection of images, labeled as cats by humans, to act as the ground truth.

By churning through it all, the AI learns, and can then identify, what makes something a cat and something not.

For deep learning vs machine learning, the key difference is that deep learning is a specific form of machine learning powered by what are called neural networks.

Neurons work in concert between your ears; a deep learning algorithm essentially does the same.

It uses multiple layers of neural networks to process the information, delivering the output we ask it to from deep within this complicated system.

Deep learning is often referred to as a "black box." Since deep learning neural networks are so complex, they can actually become too complicated to understand; we know what we put into the AI, we know what it gave us, but in the meantime, we don't know how it got to that output - that's the black box.

Deep learning uses multiple layers of neural networks to process the information, delivering the output we ask for from deep inside this complicated system.

Experts in deep learning are split on how to handle the black box.

Like computer scientist Anh Nguyen at Auburn University, he wants to crack open these boxes and figure out what makes ticks to deep learning.

In deep learning vs machine learning, when problems get tough, the former will wipe the floor with the later - and it uses that black box to do so.

Read the original article "Deep Learning versus Machine Learning:" at