The 18th European Conference on Machine Learning (ECML) and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD)

Efficient Computation of Recursive Principal Component Analysis

author: Alessandro Sperduti, Dipartimento di Matematica Pura ed Applicata, Università degli Studi di Padova

Categories

Top: Computer Science: Machine Learning: Principal Component Analysis

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Efficient Computation of Recursive Principal Component Analysis for Structured Input
0:01	Outline
1:24	What are structured domains and why are they important? (1)
1:30	What are structured domains and why are they important? (2)
1:36	What are structured domains and why are they important? (3)
1:40	What are structured domains and why are they important? (4)
1:51	What are structured domains and why are they important? (5)
1:54	Examples of Structured Data (1)
2:14	Examples of Structured Data (2)
2:22	Examples of Structured Data (3)
3:19	Vectorial Data: Principal Component Analysis
4:30	More Complex Objects
5:54	Principal Component Analysis of Sequences and Trees ?
7:02	The Strategy (1)
7:10	The Strategy (2)
7:33	The Strategy (3)
8:07	The Strategy (4)
8:31	The Strategy (5)
8:39	Sequences
11:35	Step 1: Sufficient Conditions
12:51	Sequences
12:57	Step 1: Sufficient Conditions
12:58	Step 2: Extended State Space (1)
15:11	Step 2: Extended State Space (2)
15:30	Step 2: Extended State Space (1)
15:37	Step 2: Extended State Space (2)
16:02	Step 3: Reduce (1)
16:21	Step 3: Reduce (2)
16:47	Step 3: Reduce (3)
16:52	Step 3: Reduce (4)
16:56	Step 3: Reduce (5)
16:57	Step 3: Reduce (6)
16:58	Step 3: Reduce (7)
16:59	Step 3: Reduce (8)
17:00	Step 3: Reduce (9)
17:01	Step 3: Reduce (10)
17:04	Step 3: Reduce (11)
17:13	Step 3: Reduce (12)
17:16	Step 3: Reduce (13)
17:18	Step 3: Reduce (14)
17:19	Step 3: Reduce (15)
17:21	Step 3: Reduce (16)
17:22	Step 3: Reduce (17)
17:23	Step 3: Reduce (18)
17:33	Step 3: Reduce (19)
17:56	Step 4: Compose
18:18	Recursive PCA for Trees
19:40	Graphs
20:39	The linear system for graphs
21:36	Computational Problems
23:04	Some Basic Observations and Their Exploitation
24:23	Three Techniques
25:02	Minimal State Space
27:00	Minimal DAG
28:03	QR Decomposition
28:33	Datasets for Experiments
28:46	Experiments Results
31:23	Summary
33:00	- Questions
34:10	- Questions
35:06	- Questions
36:18	- Questions
36:24	- Questions
36:56	- Questions
37:23	- Questions
37:58	- 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.