|
Size: 4606
Comment:
|
Size: 5192
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 21: | Line 21: |
| === Wednesday, 04.11.09 14.15 FR6046 === | === Wednesday, 14.4.10 14.15 FR6046 === ==== Tutorial ==== |
| Line 23: | Line 24: |
| ==== Talk ==== | '''Nicole Kraemer''' : Journal Publications |
| Line 25: | Line 26: |
| '''Aapo Hyvarinen:''' | === Wednesday, 21.4.10 14.15 FR6046 === ==== Research Ideas ==== |
| Line 27: | Line 29: |
| ''Unsupervised learning by discriminating data from artificial noise'' | * '''Paul von Buenau''', * '''Nikolay Jetchev''', * '''Bastian Venthur''' (Chair: Claudia Sannelli) |
| Line 29: | Line 34: |
| Abstract:We propose to learn the structure of data based on the simple idea of learning to discriminate data from artificially generated noise. Such learning is basically unsupervised, although we formulate it as logistic regression. The method can be shown to estimate a parametric probabilistic model for the data. Furthermore, the probabilistic model does not need to be normalized (i.e. it can be energy-based) because the normalization parameter can actually be estimated just like the other parameters. We apply the method to learning two- and three-layer networks from natural images, where the noise is white and gaussian. | === Wednesday, 28.4.10 14.15 FR6046 === ==== Research Ideas ==== * '''Daniel Bartz ''', * '''Marton Danoczy ''', * '''Stefan Haufe ''' (Chair: Alexander Binder) === Wednesday,5.5.10 14.15 FR6046 === ==== Research Ideas ==== * ''' Siamac Fazli ''', * ''' Christian Gehl''', * ''' Matthias Jugel''' (Chair: Stanimir Dragiev) |
| Line 32: | Line 51: |
| (Chair:Klaus-Robert Müller) | ==== !!! 6.-7.5. RETREAT !!! ==== |
| Line 34: | Line 53: |
=== Wednesday, 12.5.10 14.15 FR6046 === ==== Research Ideas ==== * ''' Alexander Binder''', * ''' Patrick Duessel''', * ''' Tobias Lang''' (Chair: Frank Meinecke) ==== !!! 13.-15.5. AISTATS !!! ==== === Wednesday, 19.5.10 14.15 FR6046 === ==== Research Ideas ==== * ''' Katja Hansen ''', * ''' Tammo Krueger''', * ''' Martijn Schreuder''' (Chair: Gregoire Montavon) === Wednesday, 26.5.10 14.15 FR6046 === ==== Research Ideas ==== * ''' Stanimir Dragiev''', * ''' Pascal Lehwark''', * ''' Claudia Sannelli''' (Chair: Stefan Haufe) === Wednesday, 2.6.10 14.15 FR6046 === ==== Research Ideas ==== * ''' Nils Plath''', * ''' Frank Meinecke''', * ''' n.n.''' (Chair: Bastian Venthur) ==== !!! 3.6. NIPS DEADLINE !!! ==== ---- == Previous Talks == ==== NIPS Conference Report ==== === 07.-12.12.09 NIPS === === Wednesday, 02.12.09 14.15 FR6046 === ==== Research Ideas ==== * '''Marton Danoczy''', * '''Patrick Düssel''', * '''Pascal Lehwark''' (Chair: Christian Gehl) === Wednesday, 25.11.09 14.15 FR6046 === ==== Research Ideas ==== * '''Alexander Binder''', * '''Frank Meinecke''', * '''Stefan Haufe''' (Chair:Pascal Lehwark) === Wednesday, 18.11.09 14.15 FR6046 === ==== Research Ideas ==== * '''Tammo Krüger''', * '''Katja Hansen''', * '''Elmar Diederichs''' (Chair:Felix Bießmann) |
|
| Line 44: | Line 139: |
| === Wednesday, 18.11.09 14.15 FR6046 === | |
| Line 46: | Line 140: |
| ==== Research Ideas ==== | === Wednesday, 04.11.09 14.15 FR6046 === |
| Line 48: | Line 142: |
| * '''Paul von Bünau''', * '''Katja Hansen''', * '''Tammo Krüger''' (Chair:Pascal Lehwark) |
==== Talk invited speaker ==== |
| Line 53: | Line 144: |
| === Wednesday, 25.11.09 14.15 FR6046 === | '''Aapo Hyvarinen:''' |
| Line 55: | Line 146: |
| ==== Research Ideas ==== | ''Unsupervised learning by discriminating data from artificial noise'' |
| Line 57: | Line 148: |
| * '''Alexander Binder''', * '''Frank Meinecke''', * '''Claudia Sannelli''' (Chair:Felix Bießmann) === Wednesday, 02.12.09 14.15 FR6046 === ==== Research Ideas ==== * '''Marton Danoczy''', * '''Patrick Düssel''', * '''Pascal Lehwark''' (Chair: Christian Gehl) === 07.-12.12.09 NIPS === === Wednesday, 16.12.09 14.15 FR6046 === ==== NIPS Conference Report ==== === Wednesday, 21.12.09 - 02.01.2010 no lectures === === Wednesday, 6.1.10 14.15 FR6046 === ==== Research Ideas ==== * '''Matthias Jugel''', * '''Christian Gehl''', * '''Nils Plath''' (Chair:Claudia Sanelli) === Wednesday, 13.1.10 14.15 FR6046 === ==== Research Ideas ==== * '''Siamac Fazli''', * '''Cecilia Maeder''', * '''Irene Sturm''' (Chair:Alexander Binder) === Wednesday, 20.1.10 14.15 FR6046 === ==== Research Ideas ==== * '''Bastian Venthur''', * '''Stanimir Dragiev''', * '''Grégoire Montavon''' (Chair:Matthias Jugel) === Wednesday, 27.1.10 14.15 FR6046 === ==== Research Ideas ==== * '''Anne Porbadnigk''', * '''Marko Ristin''', * '''n.n.''' (Chair:Marton Danoczy) |
Abstract: We propose to learn the structure of data based on the simple idea of learning to discriminate data from artificially generated noise. Such learning is basically unsupervised, although we formulate it as logistic regression. The method can be shown to estimate a parametric probabilistic model for the data. Furthermore, the probabilistic model does not need to be normalized (i.e. it can be energy-based) because the normalization parameter can actually be estimated just like the other parameters. We apply the method to learning two- and three-layer networks from natural images, where the noise is white and gaussian. |
| Line 115: | Line 152: |
| === Wednesday, 03.2.10 14.15 FR6046 === ==== Research Ideas ==== * '''Marton Danoczy''', * '''Patrick Düssel''', * '''Pascal Lehwark''' (Chair: Christian Gehl) |
(Chair:Klaus-Robert Müller) |
| Line 125: | Line 155: |
| ---- | |
| Line 127: | Line 156: |
| == Previous Talks == | |
| Line 164: | Line 192: |
| * [[Main/DoktorandenSeminarWS0910|Winter Term 2009 / 2010]] |
Doktoranden-/Diplomandenseminar WS 09/10
In this seminar, master/phd students of the IDA group present their current work and research ideas.
When? |
usually on Wednesdays, 2:15 pm (s.t.) to 3:15, or as announced (see below) |
Where? |
at TU Berlin , FR 6046, or as announced (see below) |
How? |
More information for speakers and participants here. |
Next Talk
Planned Talks
This is a preliminary schedule, and might be changed on short notice.
Wednesday, 14.4.10 14.15 FR6046
Tutorial
Nicole Kraemer : Journal Publications
Wednesday, 21.4.10 14.15 FR6046
Research Ideas
Paul von Buenau,
Nikolay Jetchev,
Bastian Venthur
(Chair: Claudia Sannelli)
Wednesday, 28.4.10 14.15 FR6046
Research Ideas
Daniel Bartz ,
Marton Danoczy ,
Stefan Haufe
(Chair: Alexander Binder)
Wednesday,5.5.10 14.15 FR6046
Research Ideas
Siamac Fazli ,
Christian Gehl,
Matthias Jugel
(Chair: Stanimir Dragiev)
!!! 6.-7.5. RETREAT !!!
Wednesday, 12.5.10 14.15 FR6046
Research Ideas
Alexander Binder,
Patrick Duessel,
Tobias Lang
(Chair: Frank Meinecke)
!!! 13.-15.5. AISTATS !!!
Wednesday, 19.5.10 14.15 FR6046
Research Ideas
Katja Hansen ,
Tammo Krueger,
Martijn Schreuder
(Chair: Gregoire Montavon)
Wednesday, 26.5.10 14.15 FR6046
Research Ideas
Stanimir Dragiev,
Pascal Lehwark,
Claudia Sannelli
(Chair: Stefan Haufe)
Wednesday, 2.6.10 14.15 FR6046
Research Ideas
Nils Plath,
Frank Meinecke,
n.n.
(Chair: Bastian Venthur)
!!! 3.6. NIPS DEADLINE !!!
Previous Talks
NIPS Conference Report
07.-12.12.09 NIPS
Wednesday, 02.12.09 14.15 FR6046
Research Ideas
Marton Danoczy,
Patrick Düssel,
Pascal Lehwark
(Chair: Christian Gehl)
Wednesday, 25.11.09 14.15 FR6046
Research Ideas
Alexander Binder,
Frank Meinecke,
Stefan Haufe
(Chair:Pascal Lehwark)
Wednesday, 18.11.09 14.15 FR6046
Research Ideas
Tammo Krüger,
Katja Hansen,
Elmar Diederichs
(Chair:Felix Bießmann)
Wednesday, 11.11.09 14.15 FR6046
Research Ideas
Daniel Bartz,
Felix Bießmann,
Tobias Lang
(Chair:Nils Plath)
Wednesday, 04.11.09 14.15 FR6046
Talk invited speaker
Aapo Hyvarinen:
Unsupervised learning by discriminating data from artificial noise
Abstract: We propose to learn the structure of data based on the simple idea of learning to discriminate data from artificially generated noise. Such learning is basically unsupervised, although we formulate it as logistic regression. The method can be shown to estimate a parametric probabilistic model for the data. Furthermore, the probabilistic model does not need to be normalized (i.e. it can be energy-based) because the normalization parameter can actually be estimated just like the other parameters. We apply the method to learning two- and three-layer networks from natural images, where the noise is white and gaussian.
(Chair:Klaus-Robert Müller)
Wednesday, 28.10.09 14.15 FR6046
Talk
Timon Schroeter
(Chair: Katja Hansen)
Wednesday, 21.10.09 14.15 FR6046
Research Ideas
Nikolay Jetchev: Trajectory Prediction and Parallel Exploration of Movement Trajectories for Online Planning,
Martijn Schreuder: Performance feedback during (auditory) P300 operation,
nn
(Chair:Daniel Bartz)
Wednesday, 14.10.09 14.15 FR6046
Tutorial
Matthias Treder
Experimental Design in Human Research
Abstract:This tutorial is devoted the first steps in human experimental research, that is, defining a research question and then translating this research question into an experimental design, and finally setting up the experiment. According concepts and terminology from psychological methodology are introduced, such as types of research, experimental designs, the definition of measurements, and the assessment of their quality. Possible remedies are worked out in a hopefully interactive fashion.
Archive
-- Nicole Kraemer / Katja Hansen -- Aug 2009