News

Aalto Team Win AI Research Award

Research into easier-to-interpret deep learning methods win prestigious Notable Paper award at AISTATS2019
Marcus Heinonen receiving the prize
Marcus Heinonen receiving the prize

A paper by an Aalto team, “Deep learning with differential Gaussian process flows” was awarded the 2019 Notable paper award at the 2019 AI & Statistics conference, one of only three papers to be awarded the honour out of a field of over one thousand submissions. The international congress, which took place over 3 days in Okinawa, Japan, was an opportunity for several hundred A.I. researchers from around the globe to get together and discuss their work, and FCAI researchers and students were there presenting talks and posters.

The prize winning paper was written by Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, and Samuel Kaski and came out of a collaboration between the research groups of Professor Lähdesmäki and Professor Kaski.

New methods for Deep Learning

In deep learning, hundreds of successive computations are combined together to learn very complex tasks. This how computers and phones now recognize faces in images or translate languages. In the new paper by the FCAI team, combining all the computations together is replaced with a continuous transforming flow of inputs, which are used to perform the learning task in way that’s easier to interpret. The work also presents a new connection between deep learning and a group of mathematical models called “stochastic dynamical systems”. This connection means that, compared to common neural networks, the new method can understand how much uncertainty there is in the prediction process. This understanding of uncertainty means the new method excels at learning models where there are smaller amounts of data – potentially useful for future applications like personalized medicine or drug design.

Researchers from Aalto also presented the following talks and posters:

Talks

  • Deep learning with differential Gaussian process flows

    • Pashupati Hegde,  Markus Heinonen, Harri Lähdesmäki, Samuel Kaski

Posters

  • Analysis of Network Lasso for Semi-Supervised Regression

    • Alexander Jung, Natalia Vesselinova,

  • Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution

    • Topi Paananen, Juho Piironen (Curious AI); Michael Andersen, Aki Vehtari  

  • Know Your Boundaries: Constraining Gaussian Processes by Variational Harmonic Features

    • Arno Solin  

  • Harmonizable mixture kernels with variational Fourier features

    • Zheyang Shen, Markus Heinonen, Samuel Kaski  

  • Published:
  • Updated:
Share
URL copied!

Read more news

A dog and two researchers. Photo: Aalto University/Mikko Raskinen
Research & Art Published:

Significant Academy of Finland funding for for the multidisciplinary consortium project PAWWS – People and Animal Wellbeing at Work and in Society

Astrid Huopalainen, Assistant Professor at Aalto University, Linda Tallberg, Assistant Professor at Hanken School of Economics, and Anna Hielm-Björkman, Docent at University of Helsinki, are principal investigators of the project
A teacher and two researchers smiling and sorting through paper presentations in a classroom
Research & Art Published:

Empathy in design and digitalisation – Aalto University researchers hold workshops for students at Arabia Comprehensive School

Aalto University researchers organised workshops for seventh graders, whose creative thinking skills were put to the test in designing future information services
Maja Jantar's rehearsal at Tartu Planetarium
Research & Art Published:

The Creative Europe project ‘Urban Travel Machines’ at Tartu international literary festival in Estonia

Eleven Aalto Arts students and VCD Lecturer Tarja Nieminen participated in the Tartu international literary festival Prima Vista from 9th to 13th May 2023.
Kimmo Karhu is a post-doctoral researcher at Aalto University.
Research & Art Published:

The BalticSeaH2 project starts building a hydrogen valley around the Baltic Sea

Aalto University will focus on studying the use of data-mediated network effects to boost the growth in the hydrogen valley.