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

Hands touching the surface of the rippling water.
Cooperation, Research & Art Published:

Sustainability Science Days 2023: Call for Abstracts

The SSD2023 call for abstracts is now open! Please submit an abstract to the session that you think best fits your topic by the latest February 22, 2023, at 23:59 Finnish time.
SemiSummer2023 Kampanja banneri
Cooperation, Research & Art Published:

Semiconductor sector summer jobs open in research groups

The growth of the semiconductor sector and its investments in Finland are also increasing the need for skilled personnel. Thanks to a donation from four semiconductor companies Picosun, an Applied Materials Company, Okmetic, Murata, and KYOCERA Tikitin. Aalto University will offer exciting summer jobs in the School of Electrical Engineering and the School of Chemical Engineering in the summer of 2023. Semi-Summer 2023 Programme will provide an opportunity to gain the skills needed in a growing and international field.
Sakari kuvattuna Aalto-yliopiston tiloissa.
Research & Art, Studies Published:

Sakari Poikkimäki is replacing harmful chemicals with enzymes: ‘We can use small biological organisms in many everyday products’

Chemical engineering alumnus Sakari Poikkimäki works as a fermentation expert at Roal Oy, a company that manufactures enzymes. Studies at Aalto University School of Chemical Engineering lead to a dream job where small living organisms are harnessed for good.
Iita Kejonen kuvattuna Aalto-yliopiston tiloissa.
Research & Art, Studies Published:

Iita Kejonen is involved in recycling battery metals from electric cars: ‘By working in industry, I can influence the development of the entire field’

Studies in materials science and engineering at the School of Chemical Engineering led to work with battery metals and minerals. As a Technology Manager, Iita can influence the development of responsibility in the entire automotive sector.