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:


  • Deep learning with differential Gaussian process flows

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


  • 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:
URL copied!

Related news

ARTS open science roadshow, pic of the session
Research & Art Published:

European Open Science Cloud (EOSC) Finnish Forum webinar on 25th January

One of the speakers is Karel Luyben, the first president of the EOSC Association and a member of board at Aalto University.
Installation Talk 2020, Jarkko Niiranen
Research & Art Published:

Professor Jarkko Niiranen on the computational mechanics of microarchitectural solids and structures

'When developing models, we spend a lot of time on mathematical physics, numerical mathematics and computer programming, but the fundamental concepts of mechanics remain the same' says Niiranen in his installation talk.
A photo showing Dr. Dorothea Golze
Research & Art Published:

Computational physicist Dorothea Golze receives prestigious Emmy Noether Award

Dorothea Golze received funding from the German Research Foundation within the Emmy Noether Programme to establish her own junior research group at the Technical University of Dresden.
Dronen ottama kuva Otakaari 1:sestä, kuva: Mikko Raskinen
Research & Art Published:

How do you know where a drone is flying without a GPS signal?

In Jouko Kinnari's doctoral dissertation, the location of a drone can be determined using map data and sensors.