Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tapani Raiko

A Character-Word Compositional Neural Language Model for Finnish


Dec 10, 2016
Matti Lankinen, Hannes Heikinheimo, Pyry Takala, Tapani Raiko, Juha Karhunen


  Access Paper or Ask Questions

Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters


Jun 17, 2016
Jelena Luketina, Mathias Berglund, Klaus Greff, Tapani Raiko

* 9 pages, 7 figures. Accepted at ICML 2016 

  Access Paper or Ask Questions

DopeLearning: A Computational Approach to Rap Lyrics Generation


Jun 09, 2016
Eric Malmi, Pyry Takala, Hannu Toivonen, Tapani Raiko, Aristides Gionis

* This is a pre-print of an article appearing at KDD'16 

  Access Paper or Ask Questions

Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation


Jun 07, 2016
Huiling Wang, Tapani Raiko, Lasse Lensu, Tinghuai Wang, Juha Karhunen


  Access Paper or Ask Questions

Ladder Variational Autoencoders


May 27, 2016
Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, Ole Winther


  Access Paper or Ask Questions

Semi-Supervised Learning with Ladder Networks


Nov 24, 2015
Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko

* Revised denoising function, updated results, fixed typos 

  Access Paper or Ask Questions

Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series


Nov 02, 2015
Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, Juha Karhunen


  Access Paper or Ask Questions

Lateral Connections in Denoising Autoencoders Support Supervised Learning


Apr 30, 2015
Antti Rasmus, Harri Valpola, Tapani Raiko


  Access Paper or Ask Questions

Techniques for Learning Binary Stochastic Feedforward Neural Networks


Apr 09, 2015
Tapani Raiko, Mathias Berglund, Guillaume Alain, Laurent Dinh


  Access Paper or Ask Questions

Denoising autoencoder with modulated lateral connections learns invariant representations of natural images


Mar 31, 2015
Antti Rasmus, Tapani Raiko, Harri Valpola

* Presentation at ICLR 2015 workshop 

  Access Paper or Ask Questions

Iterative Neural Autoregressive Distribution Estimator (NADE-k)


Dec 06, 2014
Tapani Raiko, Li Yao, Kyunghyun Cho, Yoshua Bengio

* Accepted at Neural Information Processing Systems (NIPS) 2014 

  Access Paper or Ask Questions

Linear State-Space Model with Time-Varying Dynamics


Oct 03, 2014
Jaakko Luttinen, Tapani Raiko, Alexander Ilin

* Machine Learning and Knowledge Discovery in Databases. Lecture Notes in Computer Science Volume 8725, 2014, pp 338-353 
* The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-662-44851-9_22 

  Access Paper or Ask Questions

Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence


Feb 14, 2014
Mathias Berglund, Tapani Raiko

* ICLR2014 Workshop Track submission. Rephrased parts of text. Results unchanged 

  Access Paper or Ask Questions

Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities


Mar 11, 2013
Tommi Vatanen, Tapani Raiko, Harri Valpola, Yann LeCun

* 10 pages, 5 figures, ICLR2013 

  Access Paper or Ask Questions

Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework


Jul 04, 2012
Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen

* Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005) 

  Access Paper or Ask Questions

'Say EM' for Selecting Probabilistic Models for Logical Sequences


Jul 04, 2012
Kristian Kersting, Tapani Raiko

* Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005) 

  Access Paper or Ask Questions

Semi-Supervised Anomaly Detection - Towards Model-Independent Searches of New Physics


Apr 16, 2012
Mikael Kuusela, Tommi Vatanen, Eric Malmi, Tapani Raiko, Timo Aaltonen, Yoshikazu Nagai

* Proceedings of ACAT 2011 conference (Uxbridge, UK), 9 pages, 4 figures 

  Access Paper or Ask Questions