Deep learning what is it?
Check the Quora answer What are the practical applications of deep learning? by Chris Nicholson, co-founder of skymind.io , co-creator of deeplearning4j.org
Deep learning is basically machine perception. What is perception? It is the power to interpret sensory data. Two main ways we interpret things are by naming what we sense; e.g. we hear a sound as we say ourselves “That’s my daughter’s voice.” Or we see a haze of photons and we say “That’s my mother’s face.” If we don’t have names for things, we can still recognize similarities and dissimilarities. You might see two faces and know that they were mother and daughter, without knowing their names; or you might hear to voices and know that they came from the same town or state by their accent. Algorithms train to name things through supervised learning, and to cluster things through unsupervised learning. The difference between supervised and unsupervised learning is whether you have a labeled training set to work with or not. The labels you apply to data are simply the outcomes you care about. Maybe you care about identifying people in images. Maybe you care about identifying angry or spammy emails, which are all just unstructured blobs of text. Maybe you’re looking at time series data — a stream of numbers — and you care about whether the next instances in the time series will be higher or lower.
So deep learning, working with other algorithms, can help you classify, cluster and predict. It does so by learning to read the signals, or structure, in data automatically. When deep learning algorithms train, they make guesses about the data, measure the error of their guesses against the training set, and then correct the way they make guesses in order to become more accurate. This is optimization.
Now imagine that, with deep learning, you can classify, cluster or predict anything you have data about: images, video, sound, text and DNA, time series (touch, stock markets, economic tables, the weather). That is, anything that humans can sense and that our technology can digitize. You have multiplied your ability to analyze what’s happening in the world by many times. With deep learning, we are basically giving society the ability to behave much more intelligently, by accurately interpreting what’s happening in the world around us with software.
Prediction alone is a huge power, and the applications are fairly obvious. Classification sounds banal, but by naming something, you can decide how to respond. If an email is spam, you send it to the spam folder and save the reader time. If the face captured by your front door camera is your mother, maybe you tell the smart lock to open the door. If a X-ray shows a tumorous pattern, you flag it for deeper examination by medical experts.
Use your imagination. We’ve prepared a short list of use cases here: