Clustering Graphs using Motifs

Lecturer : 
Event type: 
Guest lecture
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2018-03-13 14:15 to 15:00
Place: 
Description: 

Abstract:
In this talk I will present data-driven algorithms for dense subgraph discovery, and community detection respectively. The proposed algorithms leverage graph motifs to attack the large near-clique detection problem, and community detection respectively. In my talk, I will focus on triangles within graphs, but our techniques extend to other motifs as well. The intuition, that has been suggested but not formalized similarly in previous works, is that triangles are a better signature of community than edges. For both problems, we provide theoretical results, we design efficient algorithms, and then show the effectiveness of our methods to multiple applications in machine learning and graph mining.

[Joint work with Michael Mitzenmacher, and Jakub Pachocki]

Short Bio:
Dr. Charalampos Tsourakakis is an Assistant Professor at Boston University, and a Harvard Associate. He received his Ph.D. from the Algorithms, Combinatorics and Optimization (ACO) program at Carnegie Mellon University (CMU). He also holds a Master of Science from the Machine Learning Department at CMU. He did his undergraduate studies at the National Technical University of Athens (NTUA). He is the recipient of a best paper award in IEEE Data Mining, and has designed two graph mining libraries for tera-scale graphs. The former has been officially included in Windows Azure, while the latter was a research highlight of Microsoft Research. His main research interests lie in designing scalable algorithms and mining tools for large-scale datasets.

Petteri Kaski: Machine Learning Coffee seminar "Finding Outlier Correlations"

Lecturer : 
Petteri Kaski
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2018-03-12 09:15 to 10:00
Place: 
Seminar room T6, CS building, Konemiehentie 2, Otaniemi
Description: 

Petteri Kaski, Aalto University

Finding Outlier Correlations

Abstract: Finding strongly correlated pairs of observables is one of the basic tasks in data analysis and machine learning. Assuming we have N observables, there are N(N-1)/2 pairs of distinct observables, which gives rise to quadratic scalability in N if our approach is to explicitly compute all pairwise correlations.

In this talk, we look at algorithm designs that achieve subquadratic scalability in N to find pairs of observables that are strongly correlated compared with the majority of the pairs. Our plan is to start with an exposition of G. Valiant's breakthrough design [FOCS'12,JACM'15] and then look at subsequent improved designs, including some of our own work.

Based on joint work with M. Karppa, J. Kohonen, and P. Ó Catháin, cf. https://arxiv.org/abs/1510.03895 (ACM TALG, to appear) and https://arxiv.org/abs/1606.05608 (ESA'16).

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.

Welcome!

 

Machine Learning Coffee seminar "Artificial Intelligence for Mobility Studies in Urban And Natural Areas"

Lecturer : 
Tuuli Toivonen
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2018-03-05 09:15 to 10:00
Place: 
Exactum D123, Kumpula
Description: 

Tuuli Toivonen, University of Helsinki

Artificial Intelligence for Mobility Studies in Urban And Natural Areas

Abstract: Understanding how people use and move in space is important for planning, both in urban and natural areas. Recent research has shown that location-based social media data may reveal spatial and temporal patterns of the use of space, and reveal areas where human activities might be detrimental. We have shown that social media data corresponds to real-life spatial and temporal patterns of visitors in national parks and is able to bring light to use of space in cities, by providing meaningful information about the activities and preferences of people. The overwhelming magnitudes of social media data require special filtering and cleaning and tested analyses approaches. We are now using geospatial analysis methods together with machine learning to understand where, when, how and by whom areas are being used and how people and goods move about and why. Automated text and image content analysis is needed to leverage the full potential of social media data in spatial planning. Also new applications are yet to be discovered.

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.

Welcome!

Machine Learning Coffee seminar "Bayesian Deep Learning for Image Data"

Lecturer : 
Melih Kandemir
Event type: 
HIIT seminar
Doctoral dissertation
Respondent: 
Opponent: 
Custos: 
Event time: 
2018-02-26 09:15 to 10:00
Place: 
Seminar room T5, CS building, Konemiehentie 2, Otaniemi
Description: 

Melih Kandemir, Özyeğin University

Bayesian Deep Learning for Image Data

Abstract: Deep learning is the paradigm that lies at the heart of state-of-the-art machine learning approaches. Despite their groundbreaking success on a wide range of applications, deep neural nets suffer from: i) being severely prone to overfitting, ii) requiring intensive handcrafting in topology design, iii) being agnostic to model uncertainty, iv) and demanding large volumes of labeled data. The Bayesian approach provides principled solutions to all of these problems. Bayesian deep learning converts the loss minimization problem of conventional neural nets into a posterior inference problem by assigning prior distributions on synaptic weights. This talk will provide a recap of recent advances in Bayesian neural net inference and detail my contributions to the solution of this problem. I will demonstrate how Bayesian neural nets can achieve groundbreaking performance in weakly-supervised learning, active learning, few-shot learning, and transfer learning setups when applied to medical image analysis and core computer vision tasks. I will conclude by a summary of my ongoing research in reinforcement active learning, video-based imitation learning, and reconciliation of Bayesian Program Learning with Generative Adversarial Nets.

Dr. Kandemir studied computer science in Hacettepe University and Bilkent University between 2001 and 2008. Later on, he pursued his doctoral studies in Aalto University (former Helsinki University of Technology) on the development of machine learning models for mental state inference until 2013. He worked as a postdoctoral researcher in Heidelberg University, Heidelberg Collaboratory for Image Processing (HCI) between 2013 and 2016. As of 2017, he is an assistant professor at Özyeğin University, Computer Science Department. Throughout his career, he took part in various research projects in funded collaboration with multinational corporations including Nokia, Robert Bosch GmbH, and Carl Zeiss AG. Bayesian deep learning, few-shot learning, active learning, reinforcement learning, and application of these approaches to computer vision are among his research interests.

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:

  • March 5, Kumpula: Tuuli Toivonen

Welcome!

 

Machine Learning Coffee seminar "Learning and Stochastic Control in Gaussian Process Driven Physical Systems"

Lecturer : 
Simo Särkkä
Event type: 
HIIT seminar
Event time: 
2018-02-19 09:15 to 10:00
Place: 
Exactum D123, Kumpula
Description: 

Simo Särkkä, Aalto University

Learning and Stochastic Control in Gaussian Process Driven Physical Systems

Abstract: Traditional machine learning is often overemphasising problems, where we wish to automatically learn everything from the problem at hand solely using a set of training data. However, in many physical systems we already know much about the physics, typically in form of partial differential equations. For efficient learning in this kind of systems, it is beneficial to use gray-box models where only the unknown parts are modeled with data-trained machine learning models. This talk is concerned with learning and stochastic control in physical systems which contain unknown input or force signals that we wish to learn from data. These unknown signals are modeled using Gaussian processes (GP) from machine learning. The resulting latent force models (LFMs) can be seen as hybrid models that contain a first-principles physical model part and a non-parametric GP model part. We present and discuss methods for learning and stochastic control in this kind of models.

Simo Särkkä is an Associate Professor and Academy Research Fellow with Aalto University, Technical Advisor of IndoorAtlas Ltd., and an Adjunct Professor with Tampere University of Technology and Lappeenranta University of Technology. His research interests are in multi-sensor data processing systems with applications in artificial intelligence, machine learning, inverse problems, location sensing, health technology, and brain imaging. He has authored or coauthored around 100 peer-reviewed scientific articles and his book "Bayesian Filtering and Smoothing" along with its Chinese translation were published via the Cambridge University Press in 2013 and 2015, respectively. He is a Senior Member of IEEE and serving as an Associate Editor of IEEE Signal Processing Letters.

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:

  • February 26, Otaniemi: Melih Kandemir "Bayesian Deep Learning for Image Data"
  • March 5, Kumpula: Tuuli Toivonen

Welcome!

Pages