News

Silja Sormunen and Erik Härkönen received the prestigious School of Science Master’s Thesis Awards

Only about 1% of Aalto School of Science graduates received such an award
Detail from main facade of Computer Science building / Yksityiskohta Tietotekniikan talon julkisivusta / photo Aalto University, Matti Ahlgren
Two students from the Department of Computer Science received Master's Thesis Awards 2020. Photo: Matti Ahlgren / Aalto University

In February, the Aalto University School of Science presented the 2020 Master’s Thesis Awards. About 400 students graduated from the School of Science with a master’s degree, and only about one percent of them were awarded the prize.

Of the four winners, two are from the Department of Computer Science, Silja Sormunen and Erik Härkönen.

The title of Silja Sormunen's thesis is ‘Distinguishing subsampled power laws from other heavytailed distributions.’ Her thesis was supervised by Professor Jari Saramäki.

Power law distributions have frequently been observed in both natural and artificial systems, and they play a prominent role in network science. However, distinguishing power law distributions from other heavy-tailed distributions is not straight-forward, and this task is further complicated if the data is subsampled.

'In this work, we analysed how well two commonly used methods for detecting power law distributions succeed in distinguishing subsampled power laws from other heavy-tailed distributions. The thesis showed that classifying the distribution’s type correctly is challenging, but that subsampling affects the two methods’ performance differently – in fact, one of the methods can in some cases perform better on subsampled data than on the original distribution,' Sormunen explains.

Sormunen is a doctoral track student who started working on her doctoral dissertation already at the beginning of her master's studies. Read more about the doctoral track here.

The title of Erik Härkönen's master's thesis is ‘Unsupervised Discovery of Interpretable GAN Controls.’ His work was supervised by Professor Jaakko Lehtinen. The work deals with the control of data-based generative GAN machine learning models in ways that are understandable and interpretable for humans. In their basic form, GAN models are so-called black boxes, the interpretable control of which requires significant effort.

'We found out that the models can be analyzed and controlled in a simpler way than previous methods, utilizing PCA, which is a basic method of statistical analysis. Due to its unsupervised nature, the presented method also makes it possible to find completely new, previously unknown interpretable control methods,' says Härkönen.

The research work that was done for the thesis was conducted in part at Adobe Research in Cambridge, Massachusetts. The research article written about it was approved to the world’s largest and most important machine learning conference, NeurIPS, in 2020.

Read more

PML Research Group in Department of Computer Science

Doctoral track combines Master’s and doctoral studies

Top students selected to the doctoral track can have their studies tailored towards pursuing a doctoral degree and start working in the department’s research groups already during their Master’s studies.

Department of Computer Science
Silja Sormunen standing on a forest path in Otaniemi

'Mathematics is a bridge between different disciplines'

Psychology, medicine and philosophy are some of the subjects that Silja Sormunen has studied. That is why Complex Systems, part of Life Science Technologies programme, felt like just the thing she had been looking for. She is also in the Doctoral Track programme.

News
  • Published:
  • Updated:
Share
URL copied!

Read more news

Unite! online meeting
Cooperation, Studies Published:

Best practices for enhancing internationalization through virtual exchange discussed at the Unite! Staff Week

The week-long training focusing on virtual exchange was organized in February 2021 to promote internationalization between the seven universities in the Unite! network.
Yacquub Moalim Ali
Studies Published:

I am looking forward to lunch with people and seeing friends in corridors

We spoke to industrial engineering and management student Yacquub Moalim Ali about solving complex problems, the perils of watching hours of YouTube by mistake and how social distancing effected Ramadan this year
opetuksen_kehittaja_banneri_elec_fi_fi.png
Studies Published:

Nominate your choice for the Award for Quality Teaching 2020-2021

Nominate your choice for the Award for Quality Teaching at the School of Electrical Engineering.
Hertta Vuorenmaa. Kuva: Roope Kiviranta
Studies Published:

Future of Work open online course launches

Aalto University launches new open online course on the changing landscape of work.