# Most Viewed Machine Learning Talks at Videolectures

Discover lectures from a variety of summer schools and conference tutorials on machine learning in this list of the top lectures on the subject from videolectures.net.

By Grant Marshall, Sept 2014

Today, we look at the top 25 most viewed data mining lectures on videolectures.net

The way popularity is determined is by looking at the “popular” sort on the machine learning video listing. These are the videos, including authors, length, and venue, sorted by views:

One thing you’ll immediately notice about this list is the number of these lectures that come from the Machine Learning Summer Schools. Overall, more than half (thirteen out of the twenty-five) of the most popular machine learning lectures on videolectures.net come from here, taking the top four spots.

Now we will look at the titles of the videos to determine what makes a popular machine learning video.

This visualization shows a clear focus on topics like theory, modelling, and statistics - showing an affinity for the theoretical aspects of machine learning among the viewers of videolectures as opposed to more applications.

Now, we look at how the length of the lectures affect the views on the videos.

Much like the other categories of videos on videolectures, longer lengths are correlated with more views, indicating again that deeper content is more popular among videolectures’s viewers.

Today, we look at the top 25 most viewed data mining lectures on videolectures.net

The way popularity is determined is by looking at the “popular” sort on the machine learning video listing. These are the videos, including authors, length, and venue, sorted by views:

- Introduction To Bayesian Inference, Christopher Bishop, 43045 views, 2:51:04 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Machine Learning, Probability and Graphical Models, Sam Roweis, 41039 views, 1:02:45 (February 25, 2007, at Machine Learning Summer School (MLSS), Taipei 2006)
- Markov Chain Monte Carlo, Iain Murray, 37223 views, 2:27:56 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Gaussian Process Basics, David MacKay, 35956 views, 1:00:47 (February 25, 2007, at Gaussian Processes in Practice Workshop, Bletchley Park 2006)
- Support Vector Machines, Chih-Jen Lin, 32530 views, 1:17:15 (February 25, 2007, at Machine Learning Summer School (MLSS), Taipei 2006)
- Topic Models, David Blei, 26666 views, 2:57:01 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Monte Carlo Simulation for Statistical Inference, Model Selection and Decision Making, Nando de Freitas, 26596 views, 5:22:55 (March 13, 2008, at Machine Learning Summer School (MLSS), Kioloa 2008)
- Dirichlet Processes: Tutorial and Practical Course, Yee Whye The, 23579 views, 0:58:40 (August 27, 2007, at Machine Learning Summer School (MLSS), Tübingen 2007)
- A tutorial on Deep Learning, Geoffrey E. Hinton, 23489 views, 1:34:53 (September 15, 2009, at VideoLectures.NET - Single Lectures Series)
- Introduction to Support Vector Machines, Colin Campbell, 21925 views, 0:51:54 (February 5, 2008, at EPSRC Winter School in Mathematics for Data Modelling, Sheffield 2008)
- A Tutorial Introduction to Stochastic Differential Equations: Continuous-time Gaussian Markov Processes, Chris Williams, 19482 views, 0:42:43 (February 25, 2007, at NIPS Workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference, Whistler 2006)
- Probabilistic Graphical Models, Sam Roweis , 18860 views, 0:52:06 (February 25, 2007, at Machine Learning Summer School (MLSS), Canberra 2005)
- Statistical Learning Theory, John Shawe-Taylor, 15659 views, 0:48:52 (February 25, 2007, at Machine Learning Summer School (MLSS), Berder Island 2004)
- Bayesian or Frequentist, Which Are You?, Michael I. Jordan, 15612 views, 2:57:10 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Lecture 1: Introduction to Information Theory, David MacKay, 13931 views, 1:01:50 (November 5, 2012, at Course on Information Theory, Pattern Recognition, and Neural Networks)
- Information Theory, David MacKay, 13694 views, 1:26:35 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Introduction to Machine Learning, Iain Murray, 12498 views, 0:49:14 (August 5, 2010, at PASCAL Bootcamp in Machine Learning, Marseille 2010)
- An Overview of Compressed Sensing and Sparse Signal Recovery via L1 Minimization, Emmanuel Candes, 11723 views, 0:58:36 (July 30, 2009, at Machine Learning Summer School (MLSS), Chicago 2009)
- Deep Belief Networks, Geoffrey E. Hinton, 11024 views, 1:27:00 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- Particle Filters, Simon Godsill, 10744 views, 1:21:00 (November 2, 2009, at Machine Learning Summer School (MLSS), Cambridge 2009)
- How to Grow a Mind: Statistics, Structure and Abstraction, Joshua B. Tenenbaum, 4949 views, 1:09:08 (August 17, 2012, at 26th AAAI Conference on Artificial Intelligence, Toronto 2012)
- Quantum information and the Brain, Scott Aaronson, 4283 views, 0:53:11 (January 16, 2013, at 26th Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe 2012)
- Dropout: A simple and effective way to improve neural networks, Geoffrey E. Hinton, 3851 views, 0:25:19 (January 16, 2013, at 26th Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe 2012)
- Learning Representations: A Challenge for Learning Theory, Yann LeCun, 2916 views, 0:54:32 (August 9, 2013, at 26th Annual Conference on Learning Theory (COLT), Princeton 2013)
- On the Computational and Statistical Interface and "BIG DATA", Michael I. Jordan, 421 views, 0:56:26 (July 15, 2014, at 27th Annual Conference on Learning Theory (COLT), Barcelona 2014)

One thing you’ll immediately notice about this list is the number of these lectures that come from the Machine Learning Summer Schools. Overall, more than half (thirteen out of the twenty-five) of the most popular machine learning lectures on videolectures.net come from here, taking the top four spots.

Now we will look at the titles of the videos to determine what makes a popular machine learning video.

This visualization shows a clear focus on topics like theory, modelling, and statistics - showing an affinity for the theoretical aspects of machine learning among the viewers of videolectures as opposed to more applications.

Now, we look at how the length of the lectures affect the views on the videos.

Much like the other categories of videos on videolectures, longer lengths are correlated with more views, indicating again that deeper content is more popular among videolectures’s viewers.

**Related:**