The rise of Deep Learning

A couple of years ago, I was doing research involving Convolutional Neural Networks for object classification tasks (see here). At that point, deep learning was an (re)emergent field, but it hadn’t achieved mainstream yet.

Today, several factors are contributing to the increase of visibility:

  1. Announcements of great results in Kaggle competitions and commercial applications, such as Google’s improved photo search and Microsoft’s fast and robust speech recognition system.
  2. Online courses, such as Geoffrey Hinton’s “Neural Networks for Machine Learning” in Coursera.
  3. Greater variety of software implementations, including many that use the power of GPU parallelism.
What will be the next milestones?

One thought on “The rise of Deep Learning

  1. So giving a course on “deep learning” or “neural networks” is a sign of progress in the field? Or new ways of implementing these models? None of this is progress. Now as to the first point (commercial progress in image recognition and speech recognition – basically in “pattern recognition”) I concede that there was relative improvement, but this model will never scale (unless you can afford an infinite amount of time and computational resources!)

    What has happened in the last 2 years and with the muscle of Google behind this trend? NADA!

Leave a Reply

Your email address will not be published. Required fields are marked *


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Current month ye@r day *