Machine Learning Coffee seminar "Correlation-Compressed Direct Coupling Analysis"

Lecturer : 
Erik Aurell
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2017-11-27 09:15 to 10:00
Place: 
Exactum D122, Kumpula
Description: 

Erik Aurell, Professor of Biological Physics, KTH-Royal Institute of Technology

Correlation-Compressed Direct Coupling Analysis

Abstract: Direct Coupling Analysis (DCA) is a powerful tool to find pair-wise dependencies in large biological data sets. It amounts to inferring coefficients in a probabilistic model in an exponential family, and then using the largest such inferred coefficients as predictors for the dependencies of interest. The main computational bottle-neck is the inference. As described recently by Jukka Corander in this seminar series DCA has be done on bacterial whole-genome data, at the price of significant compute time, and investment in code optimization. We have looked at if DCA can be speeded up by first filtering the data on correlations, an approach we call Correlation-Compressed Direct Coupling Analysis (CC-DCA). The computational bottle-neck then moves from DCA to the more standard task of finding a subset of most strongly correlated vectors in large data sets. I will describe results obtained so far, and outline what it would take to do CC-DCA on whole-genome data in human and other higher organisms.
This is joint work with Chen-Yi Gao and Hai-Jun Zhou, available as arXiv:1710.04819.

Machine Learning Coffee seminars are weekly seminars held jointly by the Aalto University and the University of Helsinki. The seminars aim to gather people from different fields of science with interest in machine learning. Talks will begin at 9:15 am and porridge and coffee will be served from 9:00 am.

Note that we will have no talk on December 4th, 2017 (due to the NIPS conference). The following programme will be announced soon.

Welcome!

Machine Learning Coffee seminar "Towards Intelligent Exergames"

Lecturer : 
Perttu Hämäläinen
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2017-11-20 09:15 to 10:00
Place: 
Seminar room T5, CS building, Konemiehentie 2, Otaniemi
Description: 

Perttu Hämäläinen, Professor of Computer Science, Aalto University

Towards Intelligent Exergames

Abstract: Exergames - video games that require physical activity - hold promise of solving the societal hard problem of motivating people to move. At the same time, artificial intelligence and machine learning are transforming how video games are designed, produced, and tested. Work combining both computational intelligence and exergames is sparse, however. In my talk, I delineate the challenges, opportunities, and my group's research towards intelligent exergames, building on our previous research on both exergame design (e.g., Augmented Climbing Wall, Kick Ass Kung-Fu) and intelligent control of embodied simulated agents.

Machine Learning Coffee seminars are weekly seminars held jointly by the Aalto University and the University of Helsinki. The seminars aim to gather people from different fields of science with interest in machine learning. Talks will begin at 9:15 am and porridge and coffee will be served from 9:00 am.

Next talk:

Nov 27, Kumpula: Erik Aurell

Welcome!

 

Kick-off event of HiData - Helsinki Centre for Data Science

Event type: 
Event
Event time: 
2017-12-01 13:00 to 16:30
Place: 
Auditorium A111, Exactum, Kumpula campus, Gustaf Hällströmin katu 2b
Description: 
The kick-off event will present plans for HiData as well as a range of examples of data science within the participating universities. It is also a great opportunity to network with other academics with interest in data science. Anyone interested in data science research or education is welcome to join the HiData network! Also join the open Facebook group for HiData.

Data science, i.e., extraction of knowledge and insights from data, is important across many fields of science. HiData, Helsinki Centre for Data Science, aims to create a world-class research and research-based education hub of data science in Helsinki, as a joint effort between the University of Helsinki and Aalto University. HiData builds on the existing, strong research in various areas of data science, and aims to provide novel synergies across disciplines. HiData is funded in 2017-2021 as part of the profiling measures of the Academy of Finland, the University of Helsinki and Aalto University, and will get to full speed during 2018.

Please register by Nov 23th

Welcome!

More information:
Prof. Hannu Toivonen
Director of HiData
University of Helsinki 

AI Day

Event type: 
Event
Event time: 
2017-12-13 11:00 to 17:00
Place: 
Dipoli, Otakaari 24, 02150 Espoo
Description: 

Welcome to Dipoli on 13 December 2017!

The current, top-level AI research and education in Finland will be displayed during our half-day event.

Academics, welcome to present your results and network with potential private and  public sector partners!Companies, come tell about your problems that need solving!

We offer intriguing matchmaking opportunities for companies and the public sector – you are welcome to come and discuss how AI is changing the world and to discover new opportunities for your business. Meet the people at the leading edge of AI research and combine your efforts to get a head start for your organisation. 

Keynote speakers

Professor Moncef Gabbouj, Tampere University of Technology

Senior Lecturer Michael U. Gutmann, University of Edinburgh

Professor Giulio Jacucci, University of Helsinki

Professor Samuel Kaski, Aalto University

Professor Teemu Roos, University of Helsinki

See the full program here.

Registration to the event

  • For academic contributions (posters, demos, pitches) the registration deadline is 19 November.Due to time and space limitations, the organisers reserve the right to select the contributions, if necessary.
  • For reserving a small rollup demo space with table (width max 1m), please contact Terhi Kajaste at terhi.kajaste@aalto.fi for further information by 30 November.
  • For other participants the registration deadline is 5 December.

Link to the registration >>

Machine Learning Coffee seminar "Learning of Ultra High-Dimensional Potts Models for Bacterial Population Genomics"

Lecturer : 
Jukka Corander
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2017-11-13 09:15 to 10:00
Place: 
Exactum D122, Kumpula
Description: 

Jukka Corander, Professor of Statistics, University of Helsinki and University of Oslo

Learning of Ultra High-Dimensional Potts Models for Bacterial Population Genomics

Abstract: The potential for genome-wide modeling of epistasis has recently surfaced given the possibility of sequencing densely sampled populations and the emerging families of statistical interaction models. Direct coupling analysis (DCA) has earlier been shown to yield valuable predictions for single protein structures, and has recently been extended to genome-wide analysis of bacteria, identifying novel interactions in the co-evolution between resistance, virulence and core genome elements. However, earlier computational DCA methods have not been scalable to enable model fitting simultaneously to 10000-100000 polymorphisms, representing the amount of core genomic variation observed in analyses of many bacterial species. Here we introduce a novel inference method (SuperDCA) which employs a new scoring principle, efficient parallelization, optimization and filtering on phylogenetic information to achieve scalability for up to 100000 polymorphisms. Using two large population samples of Streptococcus pneumoniae, we demonstrate the ability of SuperDCA to make additional significant biological findings about this major human pathogen. We also show that our method can uncover signals of selection that are not detectable by genome-wide association analysis, even though our analysis does not require phenotypic measurements. SuperDCA thus holds considerable potential in building understanding about numerous organisms at a systems biological level.

Machine Learning Coffee seminars are weekly seminars held jointly by the Aalto University and the University of Helsinki. The seminars aim to gather people from different fields of science with interest in machine learning. Talks will begin at 9:15 am and porridge and coffee will be served from 9:00 am.

Next talks:

Nov 20, Otaniemi: Perttu Hämäläinen "Towards Intelligent Exergames"

Nov 27, Kumpula: Erik Aurell

Welcome!

 

Pages