What is Deep Learning?
Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.
What are the main reasons for the popularity of deep learning?
Main Three reasons are : accuracy, efficiency and flexibility.
Advances in hardware have made it possible to tackle problems with deep neural nets in a reasonable amount of time. Now that it’s a feasible solution, deep learning has set a lot of new records for accurate classification on benchmark datasets in recent years.
Deep learning automatically extracts features by which to classify data, as opposed to most traditional machine learning algorithms, which require intense time and effort on the part of data scientists. The features that it manages to extract are more complex than hand-crafted, because of the feature hierarchy possible in a deep net; they are also more flexible and less brittle, because the net is able to continue to learn on unsupervised data.
Deep Learning Courses
- Andrew Ng’s Coursera course provides a good introduction to deep learning (Coursera, YouTube)
- Yann LeCun’s NYU Course on Deep Learning, Spring 2014 (TechTalks)
- Geoffrey Hinton’s “Neural Networks for Machine Learning” course from Oct 2012 (Coursera)
- Rob Fergus’s “Deep Learning for Computer Vision” tutorial from NIPS 2013 (slides, video).
- Caltech’s introductory deep learning course taught by Yasser Abu-Mostafa (YouTube)
- Stanford CS224d: Deep Learning for Natural Language Processing (video, slides, tutorials)
Deep Learning Frameworks
- Caffe – Deep learning framework developed by Yangqing Jia while in the PhD program at University of California at Berkeley
- Torch – A scientific computing framework with wide support for machine learning algorithms
- Theano – A Python library that allows you to efficiently define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays
- TensorFlow – TensorFlow is an open-source software library for dataflow programming across a range of tasks. It is a symbolic math library, and also used for machine learning applications such as neural networks. It is used for both research and production at Google,