MUSCLE Conference joint with VITALAS Conference

On Sequence Kernels for SVM classification of sets of vector

author: Khalid Daoudi, INRIA

You might be experiencing some problems with Your Video player.

*Slides*
0:00	On sequence kernels for SVM classification of sets of vectors: Application to speaker verification
1:40	Text independent speaker verification - 1
1:49	Text independent speaker verification - 2
1:53	Text independent speaker verification - 3
2:01	Support vector machines (SVM) - 1
2:51	Support vector machines (SVM) - 2
2:53	- Sequence kernels
2:55	Basics on kernels
3:35	Sequence kernels - 1
4:25	Sequence kernels - 2
4:28	Mutual information kernels - 1
5:20	Mutual information kernels - 2
5:27	Mutual information kernels - 3
5:43	Kernels between probability densities
7:26	Combination of vector kernels - 1
8:07	Combination of vector kernels - 2
10:25	Combination of vector kernels - 3
10:28	- FSNS sequence kernels
10:30	Extension of the GLDS kernel : FSNS kernels - 1
11:19	Extension of the GLDS kernel : FSNS kernels - 2
12:15	Dual form of FSNS kernels - 1
12:42	Dual form of FSNS kernels - 2
13:06	Dual form of FSNS kernels - 1
13:11	Dual form of FSNS kernels - 2
13:17	Dual form of FSNS kernels - 3
13:25	Computational complexity - 1
14:18	Computational complexity - 2
14:33	Kernel approximation - 1
14:50	Kernel approximation - 2
15:21	Approximate form of FSNS kernels
16:15	- Experimental evaluation of sequence kernels
16:17	Data - 1
16:37	Data - 2
16:40	Development: Centring & Regularization?
17:36	Developement: Choice and tuning of the vector kernel
18:18	Developement: Size of the codebook
18:53	Evaluation: FSNS kernels vs. classical approches
20:01	Evaluation: Perspectives of fusion
20:35	Evaluation: All sequence kernels
22:02	Evaluation: All sequence kernels
22:23	- Questions

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.