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!

Machine Learning Coffee Seminar: "Here Be Dragons: High Dimensional Spaces and Statistical Computations"

Lecturer : 
Michael Betancourt
Event type: 
HIIT seminar
Event time: 
2018-02-12 09:15 to 10:00
Place: 
Lecture room T5, CS building, Konemiehentie 2, Otaniemi
Description: 

Michael Betancourt, Columbia University

Here Be Dragons: High-Dimensional Spaces and Statistical Computation

Abstract: With consistently growing data sets and increasingly complex models, the frontiers of applied statistics is found in high-dimensional spaces. Unfortunately most of the intuitions that we take for granted in our low-dimensional, routine experiences don’t persist to these high-dimensional spaces which makes the development of scalable computational methodologies and algorithms all the more challenging. In this talk I will discuss the counter-intuitive behavior of high-dimensional spaces and the consequences for statistical computation.

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:

February 19, Kumpula: Simo Särkkä

Welcome!

 

Machine Learning Coffee Seminar: "Studying mutational processes in cancer"

Lecturer : 
Ville Mustonen
Event type: 
HIIT seminar
Event time: 
2018-02-05 09:15 to 10:00
Place: 
Exactum D123, Kumpula
Description: 

Ville Mustonen, Professor of Computer Science, University of Helsinki

Studying mutational processes in cancer

Abstract: Somatic mutations in cancer have accumulated during its evolution and are caused by different exposures to carcinogens and therapeutic agents, as well as, intrinsic errors that occur during DNA replication. Analysing a set of cancer samples jointly allows to explain their somatic mutations as a linear combination of (to be learned) mutational signatures. In this presentation I will discuss the problem of learning mutational signatures from cancer data using probabilistic modelling and nonnegative matrix factorisation. I further describe our on going work using mutational signatures in the context of drug response prediction and extensions of the basic model to explicitly include DNA repair processes.

Machine Learning Coffee seminars are weekly seminars held jointly by the University of Helsinki and Aalto University. 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: "Confident Bayesian Learning of Graphical Models"

Lecturer : 
Mikko Koivisto
Event type: 
HIIT seminar
Event time: 
2018-01-22 09:15 to 10:00
Place: 
Exactum D123, Kumpula
Description: 

Mikko Koivisto, Associate Professor, University of Helsinki

Confident Bayesian Learning of Graphical Models

Abstract: Confident Bayesian learning amounts to computing summaries of a posterior distribution either exactly or with probabilistic accuracy guarantees. I will review the state of the art in confident Bayesian structure learning in graphical models, focusing on the class of Bayesian networks and its subclass of chordal Markov networks.

Machine Learning Coffee seminars are weekly seminars held jointly by the University of Helsinki and Aalto University. 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: 
Jan 22 Kumpula: Mikko Koivisto
Jan 29 Otaniemi: public job talks (details TBA)
Feb 5 Kumpula: Ville Mustonen
Feb 12 Otaniemi: Michael Betancourt

Welcome!

Pages