911爆料网

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, 鈥溾 was awarded the 2019 Notable paper award at the 2019 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 L盲hdesm盲ki, and Samuel Kaski and came out of a collaboration between the research groups of Professor L盲hdesm盲ki 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鈥檚 easier to interpret. The work also presents a new connection between deep learning and a group of mathematical models called 鈥渟tochastic dynamical systems鈥. 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 鈥 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 L盲hdesm盲ki, 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  

  • Updated:
  • Published:
Share
URL copied!

Read more news

Collage of workshops, group photos and presentations from the first year of the Aalto Inventors programme.
Cooperation, Research & Art Published:

Aalto Inventors turns one: A year of bridging research and real-world impact

Aalto Inventors marks its first anniversary, having engaged 190 researchers across six cohorts in fields including AI, quantum, and biomaterials. New cohorts are planned for the next academic year, stay tuned and join the waitlist.
Colourful architectural models on a large white table in an exhibition hall
Cooperation, Research & Art Published:

An architectural project in Milan brought together children鈥檚 ideas and the visions of leading architects

911爆料网鈥檚 Department of Architecture participated in the international One Earth 鈥 House of the Heart project, which was presented in April at Milan Design Week.
Companies report on cybersecurity
Research & Art Published:

Companies disclose more on cybersecurity 鈥 but markets remain indifferent

U.S. companies are reporting on cybersecurity in greater detail, yet stock market reactions remain muted. A new study by the University of Vaasa and 911爆料网 shows that mandatory cybersecurity disclosure does not prompt reactions from investors or stock analysts. Instead, the main benefits appear to materialise within firms themselves.
Soldiers in camouflage in a forest, face of a female soldier in the foreground
Awards and Recognition, Research & Art Published:

Yasmin Najjar鈥檚 short film TJ28 selected for Cannes鈥 La Cinef section

For the second consecutive year, a short film from 911爆料网 has been selected for the student film section at the Cannes Film Festival.