Biomine and network algorithms

Lecturer : 
Hannu Toivonen
Event type: 
HIIT seminar
Event time: 
2011-10-14 10:15 to 11:00
Place: 
Kumpula Exactum B222
Description: 
Talk announcement
HIIT Seminar Kumpula, Friday October 14 10:15, Exactum B222

SPEAKER:
Hannu Toivonen
University of Helsinki

TITLE:
Biomine and Network Algorithms

ABSTRACT:
tba

Focused Multi-task Learning Using Gaussian Processes

Lecturer : 
Jaakko Peltonen
Event type: 
HIIT seminar
Event time: 
2011-10-21 10:15 to 11:00
Place: 
Kumpula Exactum B222
Description: 
Talk announcement
HIIT Seminar Kumpula, Friday October 21 10:15, Exactum B222
(Please notice the new date!)

SPEAKER:
Jaakko Peltonen
Aalto University

TITLE:
Focused Multi-task Learning Using Gaussian Processes

*** This work by Gayle Leen, Jaakko Peltonen, and Samuel Kaski 
won the Award for Best Paper in Machine Learning at ECML PKDD 2011, 
the European Conference on Machine Learning and Principles and 
Practice of Knowledge Discovery in Databases. ***

ABSTRACT:
Given a learning task for a data set, learning it together with 
related tasks (data sets) can improve performance. Gaussian 
process models have been applied to such multi-task learning 
scenarios, based on joint priors for functions underlying the 
tasks. In previous Gaussian process approaches, all tasks have 
been assumed to be of equal importance, whereas in transfer 
learning the goal is asymmetric: to enhance performance on a 
target task given all other tasks. In both settings, transfer 
learning and joint modeling, negative transfer is a key problem: 
performance may actually decrease if the tasks are not related 
closely enough. In this paper, we propose a Gaussian process model 
for the asymmetric setting, which learns to “explain away” 
non-related variation in the additional tasks, in order to focus on 
improving performance on the target task. In experiments, our model 
improves performance compared to single-task learning, symmetric 
multi-task learning using hierarchical Dirichlet processes, and 
transfer learning based on predictive structure learning.

Symbol Elimination in Program Analysis

Lecturer : 
Laura Kovács
Event type: 
HIIT seminar
Event time: 
2011-09-23 10:15 to 11:00
Place: 
Kumpula Exactum B222
Description: 
Talk announcement
HIIT Seminar Kumpula, Friday September 23 10:15, Exactum B222

SPEAKER:
Laura Kovács
Vienna University of Technology

TITLE: 
Symbol Elimination in Program Analysis

ABSTRACT: 
Automatic understanding of the intended meaning of computer
programs is a very hard problem, requiring intelligence and reasoning. 
In this talk we present a new method for program analysis, called 
symbol elimination, that uses first-order theorem proving techniques 
to automatically discover non-trivial program properties, such as 
loop invariants and loop bounds. Moreover, symbol elimination can be 
used as an alternative to interpolation in software verification.

BIO:
Laura Kovács is a Hertha Firnberg Research Fellow of the Austrian Science
Fund at the Institute of Computer Languages of the Vienna University of 
Technology. Her research deals with the design and development of new
theories, technologies, and tools for program verification, with a
particular focus on automated assertion generation, symbolic summation,
computer algebra, and automated theorem proving. She holds an MSc from the
Western University of Timisoara, Romania, and a PhD degree from the
Research Institute for Symbolic Computation of the Johannes Kepler
University, Linz, Austria. Before joining TU Wien, she was a postdoctoral
researcher in the Models and Theory of Computation research group of Prof.
Dr. Thomas  A. Henzinger at the Swiss Federal Institute of Technology 
Lausanne (EPFL), and at the Programming Methodology research group of 
Prof. Dr. Peter Müller at the Swiss Federal Institute of Technology 
Zürich (ETH).

Focused Multi-task Learning Using Gaussian Processes

Lecturer : 
Jaakko Peltonen
Event type: 
HIIT seminar
Event time: 
2011-09-19 13:15 to 14:00
Place: 
Computer Science Building, Hall T2
Description: 

Our next speaker for HIIT Otaniemi seminar series is Jaakko Peltonen from the "Statistical Machine Learning and Bioinformatics" group of the Helsinki Institute for Information Technology HIIT.

All ICS@Aalto researchers are also warmly welcome to attend the seminar!

HIIT Otaniemi Seminar, Monday September 19, 13:15
Location: Computer Science Building, Hall T2

Jaakko Peltonen
Statistical Machine Learning and Bioinformatics Group
Helsinki Institute for Information Technology HIIT
Department of Information and Computer Science
Aalto University School of Science

Title:
Focused Multi-task Learning Using Gaussian Processes

*** This work by Gayle Leen, Jaakko Peltonen, and Samuel Kaski won the Award for Best Paper in Machine Learning at ECML PKDD 2011, the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ***

Abstract:
Given a learning task for a data set, learning it together with related tasks (data sets) can improve performance. Gaussian process models have been applied to such multi-task learning scenarios, based on joint priors for functions underlying the tasks. In previous Gaussian process approaches, all tasks have been assumed to be of equal importance, whereas in transfer learning the goal is asymmetric: to enhance performance on a target task given all other tasks. In both settings, transfer learning and joint modeling, negative transfer is a key problem: performance may actually decrease if the tasks are not related closely enough. In this paper, we propose a Gaussian process model for the asymmetric setting, which learns to “explain away” non-related variation in the additional tasks, in order to focus on improving performance on the target task. In experiments, our model improves performance compared to single-task learning, symmetric multi-task learning using hierarchical Dirichlet processes, and transfer learning based on predictive structure learning.

Welcome! 

-- 
Mehmet Gönen
Helsinki Institute for Information Technology HIIT
Department of Information and Computer Science
Aalto University School of Science

Deconstructing Approximate Offsets

Lecturer : 
Eric Berberich
Event type: 
HIIT seminar
Event time: 
2011-09-09 10:15 to 11:00
Place: 
Kumpula Exactum B222
Description: 
Talk announcement
HIIT Seminar Kumpula, Friday September 9 10:15, Exactum B222

SPEAKER:
Eric Berberich
Max-Planck-Institut Informatik MPII

TITLE:
Deconstructing Approximate Offsets

ABSTRACT:
Today's problem arised in a wood-cutting company that got
a new cutter. The new tools needs a smaller safety-margin
to the desired cutout. However, the only available legacy
data for the old cutter is an approximated offset, that is,
it is desired to regain the original shape before
offsetting.

Formally we study the following problem:
Can a polygonal shape Q with n vertices be expressed, up
to a tolerance eps in Hausdorff distance, as the Minkowski
sum of another polygonal shape P with a disk of fixed
radius? If it does, we also seek a preferably simple
solution shape P; its offset constitutes an accurate,
vertex-reduced and smoothened approximation of Q. We give
a decision algorithm for fixed radius in O(n log n) time
that handles any (bounded or unbounded, connected or
disconnected) polygonal shape. For convex shapes, the
complexity drops to O(n), and within the same bound, we
compute a solution shape P with at most one more vertex
than a vertex-minimal one. The talk also discusses
recent achievements as to use only rational arithmetic
for the decision and the search of good parameters
eps and r.

Pages