18 citations · 30 across the 5 of their papers we have counts for
5 papers
A Character-Word Compositional Neural Language Model for Finnish
Matti Lankinen, Hannes Heikinheimo, Pyry Takala +2
Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models. W…
Gaussian Process Kernels for Popular State-Space Time Series Models
Alexander Grigorievskiy, Juha Karhunen
In this paper we investigate a link between state- space models and Gaussian Processes (GP) for time series modeling and forecasting. In particular, several widely used state- spac…
Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
Huiling Wang, Tapani Raiko, Lasse Lensu +2
Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object s…
Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series
Mathias Berglund, Tapani Raiko, Mikko Honkala +3
Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervi…
Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework
Markus Harva, Tapani Raiko, Antti Honkela +2
A software library for constructing and learning probabilistic models is presented. The library offers a set of building blocks from which a large variety of static and dynamic mod…