Subscribe to DSC Newsletter

Deep Learning: Definition, Resources, Comparison with Machine Learning

Deep learning is sometimes referred to as the intersection between machine learning and artificial intelligence. It is about designing algorithms that can make robots intelligent, such a face recognition techniques used in drones to detect and target terrorists, or pattern recognition / computer vision algorithms to automatically pilot a plane, a train, a boat or a car.

Many deep learning algorithms (clustering, pattern recognition, automated bidding, recommendation engine, and so on)  -- even though they appear in new contexts such as IoT or machine to machine communication -- still rely on relatively old-fashioned techniques such as logistic regression, SVM, decision trees, K-NN, naive Bayes, Bayesian modeling, ensembles, random forests, signal processing, filtering, graph theory, gaming theory, and many others. Click here and here for details about the top 10 algorithms. Some are new, such as indexation algorithms to automate digital publishing, improve search engines, or create and manage large catalogs such as Amazon's product listing. 

Example of deep learning algorithms for clustering

As a result, many deep learning practitioners call themselves data scientist, computer scientist, statistician, or sometimes engineer.  In my opinion, deep learning also tries to automate some data science processes. Below are some resources to help you get started with deep learning: articles on this topic started to appear in large numbers around 2015, though many date back to before 1990. More than the technique itself, what make them interesting is the new type of applications, in which big data, fast implementation, and automation is usually involved. The articles below were all published in the last 24 months.

Resources for beginners

More advanced resources

Views: 32280

Comment

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

Join Data Science Central

Comment by Sione Palu on May 21, 2016 at 8:15pm

Quote :  "still rely on relatively old-fashioned techniques".

Some are quite new. One example is the deep non-negative matrix factorization (NMF):

"A Deep Semi-NMF Model for Learning Hidden Representations"

http://jmlr.org/proceedings/papers/v32/trigeorgis14.pdf

Follow Us

Videos

  • Add Videos
  • View All

Resources

© 2017   Data Science Central   Powered by

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