no code implementations • 22 Apr 2021 • Janne Pylkkönen, Antti Ukkonen, Juho Kilpikoski, Samu Tamminen, Hannes Heikinheimo
In this paper we show that RNN-transducer models can be effectively adapted to new domains using only small amounts of textual data.
no code implementations • 24 Jul 2017 • Andreas Henelius, Kai Puolamäki, Antti Ukkonen
In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions.
no code implementations • 20 Jan 2017 • Jussi Korpela, Emilia Oikarinen, Kai Puolamäki, Antti Ukkonen
In this paper we define confidence intervals for multivariate data that extend the one-dimensional definition in a natural way.
1 code implementation • 22 Dec 2016 • Andreas Henelius, Antti Ukkonen, Kai Puolamäki
In many data exploration tasks it is meaningful to identify groups of attribute interactions that are specific to a variable of interest.
no code implementations • 1 Dec 2016 • Ehsan Amid, Aristides Gionis, Antti Ukkonen
We consider the problem of metric learning subject to a set of constraints on relative-distance comparisons between the data items.