OPEN HOUSE on Multi-Task and Complex Outputs Learning

Estimation of gradients and coordinate covariation in classification

author: Sayan Mukherjee, Duke University

Description

We introduce an algorithm that simultaneously estimates a classification function as well as its gradient in the supervised learning framework. The motivation for the algorithm is to find salient variables and estimate how they covary. An efficient implementation with respect to both memory and time is given.

Categories

Top: Computer Science: Machine Learning: Structured Output

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Estimation of Gradients
1:52	Motivation
2:51	Motivation
3:55	Motivation
4:08	Global shrinkage estimators
4:31	Global shrinkage estimators
4:48	Global shrinkage estimators
5:05	Global shrinkage estimators
5:14	Global shrinkage estimators
5:33	Reproducing Kernel Hilbert Spaces
6:05	Reproducing Kernel Hilbert Spaces
6:37	Reproducing Kernel Hilbert Spaces
6:42	Reproducing Kernel Hilbert Spaces
6:57	Classication
7:36	Classication
8:55	Classication
9:19	Learning the gradient
10:08	Learning the gradient
10:16	Formulating the algorithm
10:43	Formulating the algorithm
11:19	Elements for algorithm
11:26	Elements for algorithm
13:21	Elements for algorithm
14:23	Gradient algorithms
14:39	Remark
14:48	Remark
15:57	Representer theorems
16:21	Representer theorems
16:56	Reducing the matrix size
17:03	Reducing the matrix size
18:36	Convergence to the gradient
20:29	Quantities of interest
20:45	Quantities of interest
21:10	Linear example
21:31	Linear example
22:14	Linear example
22:32	Linear example
22:58	Linear example
23:03	Nonlinear example
23:10	Nonlinear example
23:34	Nonlinear example
23:44	Nonlinear example
24:00	Gene expression data
24:21	Gene expression data
25:13	Decay of norms
25:28	Decay of norms
25:34	Decay of norms
26:42	Restriction to a manifold
26:53	Restriction to a manifold
27:38	Restriction to a manifold
27:52	Restriction to a manifold
28:17	Restriction to a manifold
28:51	Restriction to a manifold
29:48	Dimensionality reduction
30:11	Dimensionality reduction
30:28	Dimensionality reduction
30:58	Dimensionality reduction
31:45	Dimensionality reduction
32:11	Dimensionality reduction
33:15	Discussion
34:09	Discussion
34:32	Discussion

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

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.