T. Raiko

发表

Variational Bayesian learning of nonlinear hidden state-space models for model predictive control

Tapani Raiko, Matti Tornio, T. Raiko, 2009, Neurocomputing.

Parallel tempering is efficient for learning restricted Boltzmann machines

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

Enhanced Gradient for Training Restricted Boltzmann Machines

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2013, Neural Computation.

Application of UCT Search to the Connection Games of Hex, Y, *Star, and Renkula!

T. Raiko, J. Peltonen, 2008 .

Semi-supervised Learning with Ladder Networks

Tapani Raiko, Harri Valpola, Mikko Honkala, 2015, NIPS.

Approximate Riemannian Conjugate Gradient Learning for Fixed-Form Variational Bayes

Juha Karhunen, Antti Honkela, Tapani Raiko, 2010, J. Mach. Learn. Res..

Deep Learning Made Easier by Linear Transformations in Perceptrons

Tapani Raiko, Harri Valpola, Yann LeCun, 2012, AISTATS.

Natural Conjugate Gradient in Variational Inference

Juha Karhunen, Antti Honkela, Tapani Raiko, 2007, ICONIP.

Building Blocks for Hierarchical Latent Variable Models

J. Karhunen, T. Raiko, H. Valpola, 2001 .

Enhanced Gradient and Adaptive Learning Rate for Training Restricted Boltzmann Machines

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2011, ICML.

Iterative Neural Autoregressive Distribution Estimator NADE-k

Tapani Raiko, Li Yao, Yoshua Bengio, 2014, NIPS.

Ladder Variational Autoencoders

Ole Winther, Tapani Raiko, Casper Kaae Sønderby, 2016, NIPS.

State Inference in Variational Bayesian Nonlinear State-Space Models

Juha Karhunen, Antti Honkela, Tapani Raiko, 2006, ICA.

Improved Learning of Gaussian-Bernoulli Restricted Boltzmann Machines

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2011, ICANN.

Principal Component Analysis for Large Scale Problems with Lots of Missing Values

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2007, ECML.

Gaussian-Bernoulli deep Boltzmann machine

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

Learning nonlinear state-space models for control

T. Raiko, M. Tornio, T. Raiko, 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

Towards Super-Human Artificial Intelligence in Go by Further Improvements of AlphaGo Tapani Raiko

T. Raiko, 2016 .

CONTINUOUS REGULARIZATION HYPERPARAMETERS

T. Raiko, Mathias Berglund, Jelena Luketina, 2016 .

Higher Order Statistics in Play-out Analysis

T. Raiko, 2006 .

Bayesian ensemble learning of generative models

E. Oja, J. Karhunen, T. Raiko, 2022 .

C LOSE-TO-CLEAN REGULARIZATION RELATES VIRTUAL ADVERSARIAL TRAINING , LADDER NETWORKS AND OTHERS

Jyri J. Kivinen, T. Raiko, J. Kivinen, 2016 .

Variational Inference and Learning for Continuous-Time Nonlinear State-Space Models

J. Karhunen, T. Raiko, A. Honkela, 2008 .

Neural Information Processing (ICONIP 2013)

Tapani Raiko, Harri Valpola, Yann LeCun, 2013 .

Machine learning for signal processing 2010

Tapani Raiko, Samuel Kaski, Jaakko Peltonen, 2012, Neurocomputing.

Neurocomputing, Special Issue on Machine Learning for Signal Processing 2010, 80:1-128

Tapani Raiko, Samuel Kaski, Jaakko Peltonen, 2012 .

The NIPS workshop on Deep Learning and Unsupervised Feature Learning

Tapani Raiko, Harri Valpola, Yann LeCun, 2011 .

International Conference on Learning Representations (ICLR)

Tapani Raiko, Mudassar Abbas, Jyri Kivinen, 2016 .

Variational Bayes for Continuous-Time Nonlinear State-Space Models

T. Raiko, M. Tornio, A. Honkela, 2006 .

Proceedings of the Ninth Scandinavian Conference on Artificial Intelligence (SCAI 2006)

Tapani Raiko, Harri Valpola, Timo Honkela, 2006 .

The International Conference on Artificial Neural Networks and Machine Learning - ICANN 2013

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2013 .

Logical Hidden Markov Models (Extendes abstract)

Luc De Raedt, Tapani Raiko, Kristian Kersting, 2002, Probabilistic Graphical Models.

Advances in Independent Component Analysis and Learning Machines

Juha Karhunen, Tapani Raiko, Kyunghyun Cho, 2015 .

Bayes Blocks Software Library

Antti Honkela, Tapani Raiko, Markus Harva, 2003 .

Advances in Experimental Medicine and Biology

T. Raiko, H. Valpola, Barrie Jay, 1978 .

33rd International Conference on Machine Learning, ICML 2016

Tapani Raiko, Klaus Greff, Jelena Luketina, 2016, International Conference on Machine Learning.

ICANN Artificial Neural Networks and Machine Learning - ICANN 2012

Tapani Raiko, Roberto Calandra, Montesino Pouzols, 2012 .

European conference on machine learning and knowledge discovery in databases

Tapani Raiko, Alexander Ilin, Jaakko Luttinen, 2014 .

Two-layer contractive encodings for learning stable nonlinear features

Sven Behnke, Tapani Raiko, Kyunghyun Cho, 2015, Neural Networks.

Two-Layer Contractive Encodings with Shortcuts for Semi-supervised Learning

Sven Behnke, Tapani Raiko, Kyunghyun Cho, 2013, ICONIP.

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

Tapani Raiko, Harri Valpola, Yann LeCun, 2013, ICLR.

Tkk Reports in Information and Computer Science Practical Approaches to Principal Component Analysis in the Presence of Missing Values Tkk Reports in Information and Computer Science Practical Approaches to Principal Component Analysis in the Presence of Missing Values

Tapani Raiko, Alexander Ilin, T. Raiko, 2022 .

Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters

Tapani Raiko, Klaus Greff, Jelena Luketina, 2015, ICML.

Principal Component Analysis for Sparse High-Dimensional Data

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2007, ICONIP.

Bayesian Inference in Nonlinear and Relational Latent Variable Models

Tapani Raiko, T. Raiko, 2006 .

Chapter 7 – Unsupervised deep learning: A short review

Juha Karhunen, Tapani Raiko, Kyunghyun Cho, 2015 .

Partially observed values

T. Raiko, T. Raiko, 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

Semi-supervised anomaly detection – towards model-independent searches of new physics

Tapani Raiko, Tommi Vatanen, Timo Aaltonen, 2011, 1112.3329.

How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks pdf

Ole Winther, Tapani Raiko, Casper Kaae Sønderby, 2016, ICML 2016.

Understanding Regularization by Virtual Adversarial Training, Ladder Networks and Others

Tapani Raiko, Mudassar Abbas, Jyri Kivinen, 2016, ICLR 2016.

Building Blocks for Variational Bayesian Learning of Latent Variable Models

Juha Karhunen, Tapani Raiko, Markus Harva, 2007, J. Mach. Learn. Res..

Unsupervised deep learning

Juha Karhunen, Tapani Raiko, Kyunghyun Cho, 2015 .

Bidirectional Recurrent Neural Networks as Generative Models

Juha Karhunen, Tapani Raiko, Mikko Honkala, 2015, NIPS.

Hybrid Bilinear and Trilinear Models for Exploratory Analysis of Three-Way Poisson Counts

Tapani Raiko, Timo Honkela, Juha Raitio, 2012, ICANN.

Oscillatory neural network for image segmentation with biased competition for attention.

Tapani Raiko, Harri Valpola, T. Raiko, 2011, Advances in experimental medicine and biology.

Lateral Connections in Denoising Autoencoders Support Supervised Learning pdf

Tapani Raiko, Harri Valpola, Antti Rasmus, 2015, ArXiv.

DopeLearning: A Computational Approach to Rap Lyrics Generation

Tapani Raiko, Aristides Gionis, Hannu Toivonen, 2015, KDD.

Semi-supervised Learning with Ladder Networks pdf

Tapani Raiko, Harri Valpola, Mikko Honkala, 2015, NIPS.

ZenRobotics Recycler - Robotic Sorting using Machine Learning

Tapani Raiko, Janne V. Kujala, Timo Tossavainen, 2014 .

Learning Deep Belief Networks from Non-stationary Streams

Tapani Raiko, Marc Peter Deisenroth, Roberto Calandra, 2012, ICANN.

Missing Values in Nonlinear Factor Analysis

Tapani Raiko, Harri Valpola, T. Raiko, 2001 .

Semi-supervised detection of collective anomalies with an application in high energy particle physics

Tapani Raiko, Tommi Vatanen, Timo Aaltonen, 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

Fixed-Background EM Algorithm for Semi-Supervised Anomaly Detection

Tapani Raiko, Tommi Vatanen, Eric Malmi, 2011 .

"Say EM" for Selecting Probabilistic Models for Logical Sequences

Tapani Raiko, Kristian Kersting, K. Kersting, 2005, UAI.

A gradient-based algorithm competitive with variational Bayesian EM for mixture of Gaussians

Juha Karhunen, Antti Honkela, Tapani Raiko, 2009, 2009 International Joint Conference on Neural Networks.

Binary principal component analysis in the Netflix collaborative filtering task

Tapani Raiko, Alexander Ilin, Laszlo Kozma, 2009, 2009 IEEE International Workshop on Machine Learning for Signal Processing.

Bayesian learning of latent variable models

Juha Karhunen, Antti Honkela, Tapani Raiko, 2008 .

Chapter 2 Bayesian learning of latent variable models

J. Karhunen, T. Raiko, M. Tornio, 2008 .

Novelty detection by nonlinear factor analysis for structural health monitoring

T. Raiko, V. Lamsa, T. Raiko, 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing.

Classification Using Machine Learning and Ontologies

Tapani Raiko, Katariina Nyberg, T. Raiko, 2011 .

Computer Vision – ACCV 2018

Juha Karhunen, Tapani Raiko, Tinghuai Wang, 2018, Lecture Notes in Computer Science.

A Character-Word Compositional Neural Language Model for Finnish pdf

Juha Karhunen, Tapani Raiko, Hannes Heikinheimo, 2016, ArXiv.

Gated Boltzmann Machine in Texture Modeling

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2012, ICANN.

Techniques for Learning Binary Stochastic Feedforward Neural Networks pdf

Tapani Raiko, Laurent Dinh, Guillaume Alain, 2014, ICLR.

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

Juha Karhunen, Tapani Raiko, Mikko Honkala, 2015, ArXiv.

Semi-supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation pdf

Juha Karhunen, Tapani Raiko, Tinghuai Wang, 2016, ACCV.

Measuring the Usefulness of Hidden Units in Boltzmann Machines with Mutual Information

Tapani Raiko, Kyunghyun Cho, Mathias Berglund, 2013, ICONIP.

Logical Hidden Markov Models

L. De Raedt, K. Kersting, T. Raiko, 2011, J. Artif. Intell. Res..

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

Juha Karhunen, Antti Honkela, Tapani Raiko, 2005, UAI.

Practical Approaches to Principal Component Analysis in the Presence of Missing Values

T. Raiko, Alexander Ilin, 2010, J. Mach. Learn. Res..

Transformations for variational factor analysis to speed up learning

Tapani Raiko, Alexander Ilin, Jaakko Luttinen, 2009, ESANN.

Tikhonov-Type Regularization for Restricted Boltzmann Machines

Tapani Raiko, Alexander Ilin, Kyunghyun Cho, 2012, ICANN.

How to Pretrain Deep Boltzmann Machines in Two Stages

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2015 .

Two-Layer Contractive Encodings with Linear Transformation of Perceptrons for Semi-Supervised Learning

Sven Behnke, Tapani Raiko, Kyunghyun Cho, 2013 .

Hierarchical Variance Models of Image Sequences

Markus Harva, T. Raiko, M. Harva, 2004 .

Advances in Experimental Medicine and Biology

T. Raiko, H. Valpola, Harri Valpola, 2011 .

NIPS 2012 Workshop on Deep Learning and Unsupervised Feature Learning, Lake Tahoe, Usa, December 8, 2012

Juha Karhunen, Tapani Raiko, Alexander Ilin, 2012 .

Applications of Independent Component Analysis

Erkki Oja, E. Oja, J. Karhunen, 2004, ICONIP.

Self-organization and missing values in SOM and GTM

Matej Oresic, Tapani Raiko, Timo Honkela, 2015, Neurocomputing.