no code implementations • NoDaLiDa 2021 • Jarkko Lagus, Arto Klami
We propose an alternative for this, in form of a tool that performs lemmatization in the space of word embeddings.
1 code implementation • 5 Nov 2023 • Hanlin Yu, Marcelo Hartmann, Bernardo Williams, Mark Girolami, Arto Klami
Laplace's method approximates a target density with a Gaussian distribution at its mode.
no code implementations • 16 Aug 2023 • Marcelo Hartmann, Bernardo Williams, Hanlin Yu, Mark Girolami, Alessandro Barp, Arto Klami
We use Riemannian geometry notions to redefine the optimisation problem of a function on the Euclidean space to a Riemannian manifold with a warped metric, and then find the function's optimum along this manifold.
1 code implementation • 9 Mar 2023 • Hanlin Yu, Marcelo Hartmann, Bernardo Williams, Arto Klami
Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks.
3 code implementations • 19 Oct 2022 • Lorenzo Perini, Paul Buerkner, Arto Klami
We leverage on outputs of several anomaly detectors as a representation that already captures the basic notion of anomalousness and estimate the contamination using a specific mixture formulation.
no code implementations • 3 Oct 2022 • David Korda, Antti Penttilä, Arto Klami, Tomáš Kohout
We aim to develop a fast and robust neural-network-based method for deriving the mineral modal and chemical compositions of silicate materials from their visible and near-infrared spectra.
1 code implementation • 1 Feb 2022 • Marcelo Hartmann, Mark Girolami, Arto Klami
The efficiency of Markov Chain Monte Carlo (MCMC) depends on how the underlying geometry of the problem is taken into account.
no code implementations • 6 Dec 2021 • Krista Longi, Jakob Lindinger, Olaf Duennbier, Melih Kandemir, Arto Klami, Barbara Rakitsch
These models have a natural interpretation as discretized stochastic differential equations, but inference for long sequences with fast and slow transitions is difficult.
1 code implementation • 28 Jun 2020 • Tomasz Kuśmierczyk, Arto Klami
Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling.
no code implementations • 1 Jun 2020 • Markku Luotamo, Sari Metsämäki, Arto Klami
Semantic segmentation by convolutional neural networks (CNN) has advanced the state of the art in pixel-level classification of remote sensing images.
no code implementations • CONLL 2019 • Jarkko Lagus, Janne Sinkkonen, Arto Klami
Document embeddings, created with methods ranging from simple heuristics to statistical and deep models, are widely applicable.
2 code implementations • 27 Oct 2019 • Eliezer de Souza da Silva, Tomasz Kuśmierczyk, Marcelo Hartmann, Arto Klami
The behavior of many Bayesian models used in machine learning critically depends on the choice of prior distributions, controlled by some hyperparameters that are typically selected by Bayesian optimization or cross-validation.
1 code implementation • 11 Sep 2019 • Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications.
1 code implementation • NeurIPS 2019 • Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior.
no code implementations • NAACL 2018 • Lidia Pivovarova, Arto Klami, Roman Yangarber
We address the problem of determining entity-oriented polarity in business news.
no code implementations • SEMEVAL 2017 • Lidia Pivovarova, Lloren{\c{c}} Escoter, Arto Klami, Roman Yangarber
Task 5 of SemEval-2017 involves fine-grained sentiment analysis on financial microblogs and news.
no code implementations • 19 Apr 2017 • Joseph Sakaya, Arto Klami
Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence.
no code implementations • 21 Nov 2014 • Arto Klami, Seppo Virtanen, Eemeli Leppäaho, Samuel Kaski
Factor analysis provides linear factors that describe relationships between individual variables of a data set.
no code implementations • 2 Oct 2014 • Zakria Hussain, Arto Klami, Jussi Kujala, Alex P. Leung, Kitsuchart Pasupa, Peter Auer, Samuel Kaski, Jorma Laaksonen, John Shawe-Taylor
It then retrieves images with a specialized online learning algorithm that balances the tradeoff between exploring new images and exploiting the already inferred interests of the user.
no code implementations • 20 Dec 2013 • Arto Klami, Guillaume Bouchard, Abhishek Tripathi
CMF is a technique for simultaneously learning low-rank representations based on a collection of matrices with shared entities.