A tutorial on Deep Learning

author: Geoffrey E. Hinton, Department of Computer Science, University of Toronto
published: Sept. 15, 2009,   recorded: July 2009,   views: 228694

See Also:

Download slides icon Download slides: jul09_hinton_deeplearn.pdf (3.0┬áMB)

Help icon Streaming Video Help

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:34:54
Watch Part 2
Part 2 1:31:54


Complex probabilistic models of unlabeled data can be created by combining simpler models. Mixture models are obtained by averaging the densities of simpler models and "products of experts" are obtained by multiplying the densities together and renormalizing. A far more powerful type of combination is to form a "composition of experts" by treating the values of the latent variables of one model as the data for learning the next model. The first half of the tutorial will show how deep belief nets -- directed generative models with many layers of hidden variables -- can be learned one layer at a time by composing simple, undirected, product of expert models that only have one hidden layer. It will also explain why composing directed models does not work. Deep belief nets are trained as generative models on large, unlabeled datasets, but once multiple layers of features have been created by unsupervised learning, they can be fine-tuned to give excellent discrimination on small, labeled datasets. The second half of the tutorial will describe applications of deep belief nets to several tasks including object recognition, non-linear dimensionality reduction, document retrieval, and the interpretation of medical images. It will also show how the learning procedure for deep belief nets can be extended to high-dimensional time series and hierarchies of Conditional Random Fields.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Derrick Li, September 15, 2013 at 8:48 a.m.:

It is very good!But this lecture is difficult for me !

Comment2 omar khalid, September 21, 2015 at 2:15 p.m.:

I m looking forward to watching more from u?

Comment3 Peter, May 15, 2017 at 4:53 a.m.:

Old but still has relevant content

Comment4 Jordan, November 23, 2019 at 8:04 p.m.:

Thanks for the information on this. I really enjoy the write-up.

Here are the quickest ways to make Windows 10 dish out helpful information when something on the desktop how to get help in windows 10 leaves you stumped. n each case, Windows fetches help, either by going online, fetching built-in instructions, or leading you to a tutorial built into Windows 10.


Comment5 Diya, November 30, 2019 at 5:57 a.m.:

I enjoyed this deep learning concept.

Comment6 Asha, January 26, 2020 at 10:53 p.m.:

Getting help with file explorer in Windows 10 Configuring Windows 10 File Explorer to Open with This PC View. Step 1: First, open a new File Explorer window and click the View tab from the ribbon toolbar. Step 2: Now, click on Options, listed by default on the far right side. Step 3: In the Folder Options window, reach to the General tab and then find the drop-down box labeled Open File Explorer too. Click the drop-down How to Get Help in Windows 10 - https://windowscall.com/how-to-get-he...

Comment7 najwayaminah, March 3, 2020 at 1:21 p.m.:

Deep learning is a branch of science which is working for the Artificial intelligence and in other fields as well. Data mining and deep learning is so vast field and in which https://writingservice.ae/thesis-help also works to provide help for students.

Comment8 Goodluckastro, August 11, 2020 at 11:51 a.m.:

Good contenbt....

Comment9 Sunny, August 11, 2020 at 11:52 a.m.:

Good contenbt...

Comment10 Leo, October 9, 2020 at 3:25 p.m.:

Deep learning is an AI function that mimics the workings of the human brain in processing data for use in detecting objects, recognizing speech, translating languages, and making decisions. https://www.unmannedsas.com/

Write your own review or comment:

make sure you have javascript enabled or clear this field: