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

Jokimaisema, jossa taustalla aavikkoa. Välissä kulkee tie, jossa ajaa rekka-auto.
Press releases Published:

Humans have driven the Earth’s freshwater cycle out of its stable state

New analysis shows that the global freshwater cycle has shifted far beyond pre-industrial conditions
An artistic rendition of a photo colliding with other particles.
Studies Published:

Bridging gaps in reactor damage modelling and embracing diversity in academia

With a keen interest in electron-ion interactions, doctoral researcher Evgeniia Ponomareva describes her experience in the Nuclear Materials and Engineering (NuME) research group led by Assistant Professor Andrea Sand in the Department of Applied Physics.
Lara Ejtehadian, Patrick Rinke, and Ilari Lähteenmäki sitting with coffee mugs and smiling to the camera.
Awards and Recognition, Research & Art Published:

Aalto Open Science Award Winner 2023 - Aalto Materials Digitalization Platform (AMAD)

We interviewed the AMAD team, winners of the first Aalto Open Science Award.
Lohmann, a white female, stands in front of a lit seaweed sculpture. Laakso, a white male, seated in a metallic room with wires.
Appointments, University Published:

Sparks of curiosity: two professors share what they wonder about

Two newly tenured Aalto professors talk about what drives them