default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAapo Hyvärinen
Person information
- affiliation: University of Helsinki, Finland
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c98]Hermanni Hälvä, Jonathan So, Richard E. Turner, Aapo Hyvärinen:
Identifiable Feature Learning for Spatial Data with Nonlinear ICA. AISTATS 2024: 3331-3339- [c97]Hiroshi Morioka, Aapo Hyvärinen:
Causal Representation Learning Made Identifiable by Grouping of Observational Variables. ICML 2024 - [i41]Aapo Hyvärinen:
A noise-corrected Langevin algorithm and sampling by half-denoising. CoRR abs/2410.05837 (2024) - 2023
- [j75]Yongjie Zhu
, Tiina Parviainen, Erkka Heinilä, Lauri Parkkonen, Aapo Hyvärinen:
Unsupervised representation learning of spontaneous MEG data with nonlinear ICA. NeuroImage 274: 120142 (2023) - [j74]Aapo Hyvärinen, Ilyes Khemakhem, Hiroshi Morioka:
Nonlinear independent component analysis for principled disentanglement in unsupervised deep learning. Patterns 4(10): 100844 (2023) - [c96]Hiroshi Morioka, Aapo Hyvärinen:
Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data. AISTATS 2023: 3399-3426 - [c95]Omar Chehab, Aapo Hyvärinen, Andrej Risteski:
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond. NeurIPS 2023 - [i40]Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen:
Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation. CoRR abs/2301.09696 (2023) - [i39]Aapo Hyvärinen, Ilyes Khemakhem, Ricardo Pio Monti:
Identifiability of latent-variable and structural-equation models: from linear to nonlinear. CoRR abs/2302.02672 (2023) - [i38]Aapo Hyvärinen, Ilyes Khemakhem, Hiroshi Morioka:
Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning. CoRR abs/2303.16535 (2023) - [i37]Omar Chehab, Aapo Hyvärinen, Andrej Risteski:
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond. CoRR abs/2310.03902 (2023) - [i36]Hiroshi Morioka, Aapo Hyvärinen:
Causal Representation Learning Made Identifiable by Grouping of Observational Variables. CoRR abs/2310.15709 (2023) - [i35]Hermanni Hälvä, Jonathan So, Richard E. Turner, Aapo Hyvärinen:
Identifiable Feature Learning for Spatial Data with Nonlinear ICA. CoRR abs/2311.16849 (2023) - 2022
- [j73]Ilmari Kurki, Aapo Hyvärinen, Linda Henriksson:
Dynamics of retinotopic spatial attention revealed by multifocal MEG. NeuroImage 263: 119643 (2022) - [c94]Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen:
The optimal noise in noise-contrastive learning is not what you think. UAI 2022: 307-316 - [c93]Antti Hyttinen, Vitória Barin Pacela, Aapo Hyvärinen:
Binary independent component analysis: a non-stationarity-based approach. UAI 2022: 874-884 - [i34]Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen:
The Optimal Noise in Noise-Contrastive Learning Is Not What You Think. CoRR abs/2203.01110 (2022) - [i33]Aapo Hyvärinen:
Painful intelligence: What AI can tell us about human suffering. CoRR abs/2205.15409 (2022) - 2021
- [j72]Takeru Matsuda, Masatoshi Uehara, Aapo Hyvärinen:
Information criteria for non-normalized models. J. Mach. Learn. Res. 22: 158:1-158:33 (2021) - [j71]Wenkai Xu, Gang Niu, Aapo Hyvärinen, Masashi Sugiyama:
Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs. Neural Comput. 33(8): 2128-2162 (2021) - [c92]Hiroshi Morioka, Hermanni Hälvä, Aapo Hyvärinen:
Independent Innovation Analysis for Nonlinear Vector Autoregressive Process. AISTATS 2021: 1549-1557 - [c91]Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech, Aapo Hyvärinen:
Causal Autoregressive Flows. AISTATS 2021: 3520-3528 - [c90]Alexandre Gramfort, Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis A. Engemann:
Learning with self-supervision on EEG data. BCI 2021: 1-2 - [c89]Hermanni Hälvä, Sylvain Le Corff, Luc Lehéricy, Jonathan So, Yongjie Zhu, Elisabeth Gassiat, Aapo Hyvärinen:
Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA. NeurIPS 2021: 1624-1633 - [c88]Hugo Richard, Pierre Ablin, Bertrand Thirion, Alexandre Gramfort, Aapo Hyvärinen:
Shared Independent Component Analysis for Multi-Subject Neuroimaging. NeurIPS 2021: 29962-29971 - [i32]Hugo Richard, Pierre Ablin, Aapo Hyvärinen, Alexandre Gramfort, Bertrand Thirion:
Adaptive Multi-View ICA: Estimation of noise levels for optimal inference. CoRR abs/2102.10964 (2021) - [i31]Hermanni Hälvä, Sylvain Le Corff, Luc Lehéricy, Jonathan So, Yongjie Zhu, Elisabeth Gassiat, Aapo Hyvärinen:
Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA. CoRR abs/2106.09620 (2021) - [i30]Hugo Richard, Pierre Ablin, Bertrand Thirion, Alexandre Gramfort, Aapo Hyvärinen:
Shared Independent Component Analysis for Multi-Subject Neuroimaging. CoRR abs/2110.13502 (2021) - [i29]Antti Hyttinen, Vitória Barin Pacela, Aapo Hyvärinen:
Binary Independent Component Analysis via Non-stationarity. CoRR abs/2111.15431 (2021) - 2020
- [j70]Hiroshi Morioka, Vince D. Calhoun, Aapo Hyvärinen:
Nonlinear ICA of fMRI reveals primitive temporal structures linked to rest, task, and behavioral traits. NeuroImage 218: 116989 (2020) - [j69]Miika Koskinen, Mikko Kurimo, Joachim Gross, Aapo Hyvärinen, Riitta Hari:
Brain activity reflects the predictability of word sequences in listened continuous speech. NeuroImage 219: 116936 (2020) - [c87]Ilyes Khemakhem, Diederik P. Kingma, Ricardo Pio Monti, Aapo Hyvärinen:
Variational Autoencoders and Nonlinear ICA: A Unifying Framework. AISTATS 2020: 2207-2217 - [c86]Thuc Duy Le, Lin Liu, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvärinen:
Preface: The 2020 ACM SIGKDD Workshop on Causal Discovery. CD@KDD 2020: 1-3 - [c85]Luigi Gresele, Giancarlo Fissore, Adrián Javaloy, Bernhard Schölkopf, Aapo Hyvärinen:
Relative gradient optimization of the Jacobian term in unsupervised deep learning. NeurIPS 2020 - [c84]Ilyes Khemakhem, Ricardo Pio Monti, Diederik P. Kingma, Aapo Hyvärinen:
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA. NeurIPS 2020 - [c83]Hugo Richard, Luigi Gresele, Aapo Hyvärinen, Bertrand Thirion, Alexandre Gramfort, Pierre Ablin:
Modeling Shared responses in Neuroimaging Studies through MultiView ICA. NeurIPS 2020 - [c82]Hiroaki Sasaki, Takashi Takenouchi, Ricardo Pio Monti, Aapo Hyvärinen:
Robust contrastive learning and nonlinear ICA in the presence of outliers. UAI 2020: 659-668 - [c81]Hermanni Hälvä, Aapo Hyvärinen:
Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series. UAI 2020: 939-948 - [e3]Thuc Duy Le, Lin Liu, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvärinen:
Proceedings of the 2020 KDD Workshop on Causal Discovery (CD@KDD 2020), San Diego, CA, USA, 24 August 2020. Proceedings of Machine Learning Research 127, PMLR 2020 [contents] - [i28]Ilyes Khemakhem, Ricardo Pio Monti, Diederik P. Kingma, Aapo Hyvärinen:
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models. CoRR abs/2002.11537 (2020) - [i27]Hugo Richard, Luigi Gresele, Aapo Hyvärinen, Bertrand Thirion, Alexandre Gramfort, Pierre Ablin:
Modeling Shared Responses in Neuroimaging Studies through MultiView ICA. CoRR abs/2006.06635 (2020) - [i26]Hiroshi Morioka, Aapo Hyvärinen:
Independent innovation analysis for nonlinear vector autoregressive process. CoRR abs/2006.10944 (2020) - [i25]Hermanni Hälvä, Aapo Hyvärinen:
Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series. CoRR abs/2006.12107 (2020) - [i24]Luigi Gresele, Giancarlo Fissore, Adrián Javaloy, Bernhard Schölkopf, Aapo Hyvärinen:
Relative gradient optimization of the Jacobian term in unsupervised deep learning. CoRR abs/2006.15090 (2020) - [i23]Ricardo Pio Monti, Ilyes Khemakhem, Aapo Hyvärinen:
Autoregressive flow-based causal discovery and inference. CoRR abs/2007.09390 (2020) - [i22]Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis-Alexander Engemann, Alexandre Gramfort:
Uncovering the structure of clinical EEG signals with self-supervised learning. CoRR abs/2007.16104 (2020) - [i21]Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech, Aapo Hyvärinen:
Causal Autoregressive Flows. CoRR abs/2011.02268 (2020)
2010 – 2019
- 2019
- [j68]Saeed Saremi, Aapo Hyvärinen:
Neural Empirical Bayes. J. Mach. Learn. Res. 20: 181:1-181:23 (2019) - [j67]Alexander Y. Zhigalov, Erkka Heinilä, Tiina Parviainen, Lauri Parkkonen, Aapo Hyvärinen:
Decoding attentional states for neurofeedback: Mindfulness vs. wandering thoughts. NeuroImage 185: 565-574 (2019) - [c80]Aapo Hyvärinen, Hiroaki Sasaki, Richard E. Turner:
Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning. AISTATS 2019: 859-868 - [c79]Takeru Matsuda, Aapo Hyvärinen:
Estimation of Non-Normalized Mixture Models. AISTATS 2019: 2555-2563 - [c78]Thuc Duy Le, Jiuyong Li, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvärinen:
Preface: The 2019 ACM SIGKDD Workshop on Causal Discovery. CD@KDD 2019: 1-3 - [c77]Hubert J. Banville, Graeme Moffat, Isabela Albuquerque, Denis-Alexander Engemann, Aapo Hyvärinen, Alexandre Gramfort:
Self-Supervised Representation Learning from Electroencephalography Signals. MLSP 2019: 1-6 - [c76]Ricardo Pio Monti, Kun Zhang, Aapo Hyvärinen:
Causal Discovery with General Non-Linear Relationships using Non-Linear ICA. UAI 2019: 186-195 - [e2]Thuc Duy Le, Jiuyong Li, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvärinen:
Proceedings of the 2019 ACM SIGKDD Workshop on Causal Discovery, CD@KDD 2019, Anchorage, Alaska, USA, August 5, 2019. Proceedings of Machine Learning Research 104, PMLR 2019 [contents] - [i20]Saeed Saremi, Aapo Hyvärinen:
Neural Empirical Bayes. CoRR abs/1903.02334 (2019) - [i19]Ricardo Pio Monti, Kun Zhang, Aapo Hyvärinen:
Causal Discovery with General Non-Linear Relationships Using Non-Linear ICA. CoRR abs/1904.09096 (2019) - [i18]Takeru Matsuda, Masatoshi Uehara, Aapo Hyvärinen:
Information criteria for non-normalized models. CoRR abs/1905.05976 (2019) - [i17]Ilyes Khemakhem, Diederik P. Kingma, Aapo Hyvärinen:
Variational Autoencoders and Nonlinear ICA: A Unifying Framework. CoRR abs/1907.04809 (2019) - [i16]Wenkai Xu, Gang Niu, Aapo Hyvärinen, Masashi Sugiyama:
Direction Matters: On Influence-Preserving Graph Summarization and Max-cut Principle for Directed Graphs. CoRR abs/1907.09588 (2019) - [i15]Hiroaki Sasaki, Takashi Takenouchi, Ricardo Pio Monti, Aapo Hyvärinen:
Robust contrastive learning and nonlinear ICA in the presence of outliers. CoRR abs/1911.00265 (2019) - [i14]Hubert J. Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort:
Self-supervised representation learning from electroencephalography signals. CoRR abs/1911.05419 (2019) - 2018
- [c75]Thuc Duy Le, Kun Zhang, Emre Kiciman, Aapo Hyvärinen, Lin Liu:
Preface: The 2018 ACM SIGKDD Workshop on Causal Discovery. CD@KDD 2018: 1-3 - [c74]Ricardo Pio Monti, Aapo Hyvärinen:
A unified probabilistic model for learning latent factors and their connectivities from high-dimensional data . UAI 2018: 300-309 - [e1]Thuc Duy Le, Kun Zhang, Emre Kiciman, Aapo Hyvärinen, Lin Liu:
Proceedings of 2018 ACM SIGKDD Workshop on Causal Discovery, CD@KDD 2018, London, UK, 20 August 2018. Proceedings of Machine Learning Research 92, PMLR 2018 [contents] - [i13]Takeru Matsuda, Aapo Hyvärinen:
Estimation of Non-Normalized Mixture Models and Clustering Using Deep Representation. CoRR abs/1805.07516 (2018) - [i12]Saeed Saremi, Arash Mehrjou, Bernhard Schölkopf, Aapo Hyvärinen:
Deep Energy Estimator Networks. CoRR abs/1805.08306 (2018) - [i11]Aapo Hyvärinen, Hiroaki Sasaki, Richard E. Turner:
Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning. CoRR abs/1805.08651 (2018) - [i10]Ricardo Pio Monti, Aapo Hyvärinen:
A Unified Probabilistic Model for Learning Latent Factors and Their Connectivities from High-Dimensional Data. CoRR abs/1805.09567 (2018) - [i9]Hiroaki Sasaki, Aapo Hyvärinen:
Neural-Kernelized Conditional Density Estimation. CoRR abs/1806.01754 (2018) - 2017
- [j66]Bharath K. Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Aapo Hyvärinen, Revant Kumar:
Density Estimation in Infinite Dimensional Exponential Families. J. Mach. Learn. Res. 18: 57:1-57:59 (2017) - [j65]Hiroaki Sasaki, Takafumi Kanamori, Aapo Hyvärinen, Gang Niu, Masashi Sugiyama:
Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios. J. Mach. Learn. Res. 18: 180:1-180:47 (2017) - [j64]Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvärinen:
Simultaneous Estimation of Nongaussian Components and Their Correlation Structure. Neural Comput. 29(11) (2017) - [j63]Haruo Hosoya, Aapo Hyvärinen:
A mixture of sparse coding models explaining properties of face neurons related to holistic and parts-based processing. PLoS Comput. Biol. 13(7) (2017) - [c73]Aapo Hyvärinen, Hiroshi Morioka:
Nonlinear ICA of Temporally Dependent Stationary Sources. AISTATS 2017: 460-469 - [c72]Hande Çelikkanat, Hiroki Moriya, Takeshi Ogawa, Jukka-Pekka Kauppi, Motoaki Kawanabe, Aapo Hyvärinen:
Decoding emotional valence from electroencephalographic rhythmic activity. EMBC 2017: 4143-4146 - [c71]Junichiro Hirayama, Aapo Hyvärinen, Motoaki Kawanabe:
SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling. ICML 2017: 1491-1500 - 2016
- [j62]Junichiro Hirayama, Aapo Hyvärinen, Shin Ishii:
Sparse and low-rank matrix regularization for learning time-varying Markov networks. Mach. Learn. 105(3): 335-366 (2016) - [j61]Aapo Hyvärinen, Junichiro Hirayama, Vesa Kiviniemi, Motoaki Kawanabe:
Orthogonal Connectivity Factorization: Interpretable Decomposition of Variability in Correlation Matrices. Neural Comput. 28(3): 445-484 (2016) - [j60]Haruo Hosoya, Aapo Hyvärinen:
Learning Visual Spatial Pooling by Strong PCA Dimension Reduction. Neural Comput. 28(7): 1249-1264 (2016) - [c70]Aapo Hyvärinen, Hiroshi Morioka:
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA. NIPS 2016: 3765-3773 - [i8]Aapo Hyvärinen, Hiroshi Morioka:
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA. CoRR abs/1605.06336 (2016) - 2015
- [j59]Junichiro Hirayama, Takeshi Ogawa, Aapo Hyvärinen:
Unifying Blind Separation and Clustering for Resting-State EEG/MEG Functional Connectivity Analysis. Neural Comput. 27(7): 1373-1404 (2015) - [c69]Jouni Puuronen, Aapo Hyvärinen:
Independent component analysis with an inverse problem motivated penalty term. IJCNN 2015: 1-7 - 2014
- [j58]Tatsuya Tashiro, Shohei Shimizu, Aapo Hyvärinen, Takashi Washio:
ParceLiNGAM: A Causal Ordering Method Robust Against Latent Confounders. Neural Comput. 26(1): 57-83 (2014) - [j57]Pavan Ramkumar, Lauri Parkkonen, Aapo Hyvärinen:
Group-level spatial independent component analysis of Fourier envelopes of resting-state MEG data. NeuroImage 86: 480-491 (2014) - [j56]Stephen M. Smith, Aapo Hyvärinen, Gaël Varoquaux, Karla L. Miller, Christian F. Beckmann:
Group-PCA for very large fMRI datasets. NeuroImage 101: 738-749 (2014) - [j55]Jouni Puuronen, Aapo Hyvärinen:
A Bayesian inverse solution using independent component analysis. Neural Networks 50: 47-59 (2014) - [c68]Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvärinen:
Estimating Dependency Structures for non-Gaussian Components with Linear and Energy Correlations. AISTATS 2014: 868-876 - [c67]Junichiro Hirayama, Takeshi Ogawa, Aapo Hyvärinen:
Simultaneous blind separation and clustering of coactivated EEG/MEG sources for analyzing spontaneous brain activity. EMBC 2014: 4932-4935 - [c66]Hiroaki Sasaki, Aapo Hyvärinen, Masashi Sugiyama:
Clustering via Mode Seeking by Direct Estimation of the Gradient of a Log-Density. ECML/PKDD (3) 2014: 19-34 - [c65]Aapo Hyvärinen, Junichiro Hirayama, Motoaki Kawanabe:
Dynamic connectivity factorization: Interpretable decompositions of non-stationarity. PRNI 2014: 1-4 - [r2]Aapo Hyvärinen:
Independent Component Analysis of Images. Encyclopedia of Computational Neuroscience 2014 - [r1]Aapo Hyvärinen:
Topographic Independent Component Analysis. Encyclopedia of Computational Neuroscience 2014 - [i7]Shohei Shimizu, Aapo Hyvärinen, Yoshinobu Kawahara:
A direct method for estimating a causal ordering in a linear non-Gaussian acyclic model. CoRR abs/1408.2038 (2014) - 2013
- [j54]Aapo Hyvärinen, Stephen M. Smith:
Pairwise likelihood ratios for estimation of non-Gaussian structural equation models. J. Mach. Learn. Res. 14(1): 111-152 (2013) - [j53]Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvärinen:
Correlated topographic analysis: estimating an ordering of correlated components. Mach. Learn. 92(2-3): 285-317 (2013) - [j52]Jukka-Pekka Kauppi, Lauri Parkkonen, Riitta Hari, Aapo Hyvärinen:
Decoding magnetoencephalographic rhythmic activity using spectrospatial information. NeuroImage 83: 921-936 (2013) - [i6]Kun Zhang, Heng Peng, Laiwan Chan, Aapo Hyvärinen:
Bridging Information Criteria and Parameter Shrinkage for Model Selection. CoRR abs/1307.2307 (2013) - 2012
- [j51]Michael Gutmann, Aapo Hyvärinen:
Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics. J. Mach. Learn. Res. 13: 307-361 (2012) - [c64]Tatsuya Tashiro, Shohei Shimizu, Aapo Hyvärinen, Takashi Washio:
Estimation of Causal Orders in a Linear Non-Gaussian Acyclic Model: A Method Robust against Latent Confounders. ICANN (1) 2012: 491-498 - [c63]Michael Gutmann, Aapo Hyvärinen:
Learning a selectivity-invariance-selectivity feature extraction architecture for images. ICPR 2012: 918-921 - [c62]Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvärinen:
Topographic Analysis of Correlated Components. ACML 2012: 365-378 - [i5]Miika Pihlaja, Michael Gutmann, Aapo Hyvärinen:
A Family of Computationally Efficient and Simple Estimators for Unnormalized Statistical Models. CoRR abs/1203.3506 (2012) - [i4]Kun Zhang, Aapo Hyvärinen:
Source Separation and Higher-Order Causal Analysis of MEG and EEG. CoRR abs/1203.3533 (2012) - [i3]Kun Zhang, Aapo Hyvärinen:
On the Identifiability of the Post-Nonlinear Causal Model. CoRR abs/1205.2599 (2012) - [i2]Patrik O. Hoyer, Aapo Hyvärinen, Richard Scheines, Peter Spirtes, Joseph D. Ramsey, Gustavo Lacerda, Shohei Shimizu:
Causal discovery of linear acyclic models with arbitrary distributions. CoRR abs/1206.3260 (2012) - [i1]Shohei Shimizu, Aapo Hyvärinen, Yutaka Kano, Patrik O. Hoyer:
Discovery of non-gaussian linear causal models using ICA. CoRR abs/1207.1413 (2012) - 2011
- [j50]Shohei Shimizu, Takanori Inazumi, Yasuhiro Sogawa, Aapo Hyvärinen, Yoshinobu Kawahara, Takashi Washio, Patrik O. Hoyer, Kenneth Bollen:
DirectLiNGAM: A Direct Method for Learning a Linear Non-Gaussian Structural Equation Model. J. Mach. Learn. Res. 12: 1225-1248 (2011) - [j49]Aapo Hyvärinen:
Testing the ICA mixing matrix based on inter-subject or inter-session consistency. NeuroImage 58(1): 122-136 (2011) - [j48]Yasuhiro Sogawa, Shohei Shimizu, Teppei Shimamura, Aapo Hyvärinen, Takashi Washio, Seiya Imoto:
Estimating exogenous variables in data with more variables than observations. Neural Networks 24(8): 875-880 (2011) - [c61]Jouni Puuronen, Aapo Hyvärinen:
Hermite Polynomials and Measures of Non-gaussianity. ICANN (2) 2011: 205-212 - [c60]Valero Laparra, Michael Gutmann, Jesús Malo, Aapo Hyvärinen:
Complex-Valued Independent Component Analysis of Natural Images. ICANN (2) 2011: 213-220 - [c59]Michael Gutmann, Aapo Hyvärinen:
Extracting Coactivated Features from Multiple Data Sets. ICANN (1) 2011: 323-330 - [c58]Junichiro Hirayama, Aapo Hyvärinen:
Structural equations and divisive normalization for energy-dependent component analysis. NIPS 2011: 1872-1880 - [c57]Kun Zhang, Aapo Hyvärinen:
A General Linear Non-Gaussian State-Space Model. ACML 2011: 113-128 - 2010
- [j47]Aapo Hyvärinen, Kun Zhang, Shohei Shimizu, Patrik O. Hoyer:
Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity. J. Mach. Learn. Res. 11: 1709-1731 (2010) - [j46]Urs Köster, Aapo Hyvärinen:
A Two-Layer Model of Natural Stimuli Estimated with Score Matching. Neural Comput. 22(9): 2308-2333 (2010) - [j45]Aapo Hyvärinen, Pavan Ramkumar, Lauri Parkkonen, Riitta Hari:
Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis. NeuroImage 49(1): 257-271 (2010) - [j44]Timo Honkela, Aapo Hyvärinen, Jaakko J. Väyrynen:
WordICA - emergence of linguistic representations for words by independent component analysis. Nat. Lang. Eng. 16(3): 277-308 (2010) - [j43]Aapo Hyvärinen:
Statistical Models of Natural Images and Cortical Visual Representation. Top. Cogn. Sci. 2(2): 251-264 (2010) - [c56]Yasuhiro Sogawa, Shohei Shimizu, Aapo Hyvärinen, Takashi Washio, Teppei Shimamura, Seiya Imoto:
Discovery of Exogenous Variables in Data with More Variables Than Observations. ICANN (1) 2010: 67-76 - [c55]Junichiro Hirayama, Aapo Hyvärinen, Shin Ishii:
Sparse and Low-Rank Estimation of Time-Varying Markov Networks with Alternating Direction Method of Multipliers. ICONIP (1) 2010: 371-379 - [c54]Miika Pihlaja, Michael Gutmann, Aapo Hyvärinen:
A Family of Computationally E cient and Simple Estimators for Unnormalized Statistical Models. UAI 2010: 442-449 - [c53]Kun Zhang, Aapo Hyvärinen:
Source Separation and Higher-Order Causal Analysis of MEG and EEG. UAI 2010: 709-716 - [c52]Aapo Hyvärinen:
Pairwise Measures of Causal Direction in Linear Non-Gaussian Acyclic Models. ACML 2010: 1-16 - [c51]Kun Zhang, Aapo Hyvärinen:
Nonlinear acyclic causal models. NIPS Causality: Objectives and Assessment 2010: 157-164 - [c50]Michael Gutmann, Aapo Hyvärinen:
Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. AISTATS 2010: 297-304
2000 – 2009
- 2009
- [b2]Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer:
Natural Image Statistics - A Probabilistic Approach to Early Computational Vision. Computational Imaging and Vision 39, Springer 2009, ISBN 978-1-84882-490-4, pp. 1-451 - [j42]Shohei Shimizu, Patrik O. Hoyer, Aapo Hyvärinen:
Estimation of linear non-Gaussian acyclic models for latent factors. Neurocomputing 72(7-9): 2024-2027 (2009) - [c49]Michael Gutmann, Aapo Hyvärinen:
Learning reconstruction and prediction of natural stimuli by a population of spiking neurons. ESANN 2009 - [c48]Michael Gutmann, Aapo Hyvärinen:
Learning Features by Contrasting Natural Images with Noise. ICANN (2) 2009: 623-632 - [c47]Jukka Perkiö, Aapo Hyvärinen:
Modelling Image Complexity by Independent Component Analysis, with Application to Content-Based Image Retrieval. ICANN (2) 2009: 704-714 - [c46]Kun Zhang, Heng Peng, Laiwan Chan, Aapo Hyvärinen:
ICA with Sparse Connections: Revisited. ICA 2009: 195-202 - [c45]Urs Köster, Jussi T. Lindgren, Michael Gutmann, Aapo Hyvärinen:
Learning Natural Image Structure with a Horizontal Product Model. ICA 2009: 507-514 - [c44]Urs Köster, Jussi T. Lindgren, Aapo Hyvärinen:
Estimating Markov Random Field Potentials for Natural Images. ICA 2009: 515-522 - [c43]Kun Zhang, Aapo Hyvärinen:
Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective. ECML/PKDD (2) 2009: 570-585 - [c42]Shohei Shimizu, Aapo Hyvärinen, Yoshinobu Kawahara:
A direct method for estimating a causal ordering in a linear non-Gaussian acyclic model. UAI 2009: 506-513 - [c41]Kun Zhang, Aapo Hyvärinen:
On the Identifiability of the Post-Nonlinear Causal Model. UAI 2009: 647-655 - 2008
- [j41]Aapo Hyvärinen:
Optimal Approximation of Signal Priors. Neural Comput. 20(12): 3087-3110 (2008) - [c40]Aapo Hyvärinen, Shohei Shimizu, Patrik O. Hoyer:
Causal modelling combining instantaneous and lagged effects: an identifiable model based on non-Gaussianity. ICML 2008: 424-431 - [c39]Michael Gutmann, Aapo Hyvärinen, Kazuyuki Aihara:
Learning encoding and decoding filters for data representation with a spiking neuron. IJCNN 2008: 243-248 - [c38]Jussi T. Lindgren, Jarmo Hurri, Aapo Hyvärinen:
Unsupervised learning of dependencies between local luminance and contrast in natural images. IJCNN 2008: 356-362 - [c37]Jussi T. Lindgren, Aapo Hyvärinen:
On the learning of nonlinear visual features from natural images by optimizing response energies. IJCNN 2008: 1026-1033 - [c36]Patrik O. Hoyer, Aapo Hyvärinen, Richard Scheines, Peter Spirtes, Joseph D. Ramsey, Gustavo Lacerda, Shohei Shimizu:
Causal discovery of linear acyclic models with arbitrary distributions. UAI 2008: 282-289 - 2007
- [j40]Aapo Hyvärinen:
Some extensions of score matching. Comput. Stat. Data Anal. 51(5): 2499-2512 (2007) - [j39]Maria Asunción Vicente, Patrik O. Hoyer, Aapo Hyvärinen:
Equivalence of Some Common Linear Feature Extraction Techniques for Appearance-Based Object Recognition Tasks. IEEE Trans. Pattern Anal. Mach. Intell. 29(5): 896-900 (2007) - [j38]Aapo Hyvärinen:
Connections Between Score Matching, Contrastive Divergence, and Pseudolikelihood for Continuous-Valued Variables. IEEE Trans. Neural Networks 18(5): 1529-1531 (2007) - [c35]Urs Köster, Aapo Hyvärinen:
A Two-Layer ICA-Like Model Estimated by Score Matching. ICANN (2) 2007: 798-807 - [c34]Shohei Shimizu, Aapo Hyvärinen:
Discovery of Linear Non-Gaussian Acyclic Models in the Presence of Latent Classes. ICONIP (1) 2007: 752-761 - [c33]Jussi T. Lindgren, Jarmo Hurri, Aapo Hyvärinen:
The Statistical Properties of Local Log-Contrast in Natural Images. SCIA 2007: 354-363 - 2006
- [j37]Shohei Shimizu, Aapo Hyvärinen, Patrik O. Hoyer, Yutaka Kano:
Finding a causal ordering via independent component analysis. Comput. Stat. Data Anal. 50(11): 3278-3293 (2006) - [j36]Shohei Shimizu, Patrik O. Hoyer, Aapo Hyvärinen, Antti J. Kerminen:
A Linear Non-Gaussian Acyclic Model for Causal Discovery. J. Mach. Learn. Res. 7: 2003-2030 (2006) - [j35]Aapo Hyvärinen:
Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines. Neural Comput. 18(10): 2283-2292 (2006) - [c32]Aapo Hyvärinen, Urs Köster:
FastISA: A fast fixed-point algorithm for independent subspace analysis. ESANN 2006: 371-376 - [c31]Patrik O. Hoyer, Shohei Shimizu, Aapo Hyvärinen, Yutaka Kano, Antti J. Kerminen:
New Permutation Algorithms for Causal Discovery Using ICA. ICA 2006: 115-122 - [c30]Shohei Shimizu, Aapo Hyvärinen, Yutaka Kano, Patrik O. Hoyer, Antti J. Kerminen:
Testing Significance of Mixing and Demixing Coefficients in ICA. ICA 2006: 901-908 - [c29]Aapo Hyvärinen, Shohei Shimizu:
A Quasi-stochastic Gradient Algorithm for Variance-Dependent Component Analysis. ICANN (2) 2006: 211-220 - [c28]Aapo Hyvärinen, Jukka Perkiö:
Learning to Segment Any Random Vector. IJCNN 2006: 4167-4172 - [c27]Jussi T. Lindgren, Aapo Hyvärinen:
Emergence of conjunctive visual features by quadratic independent component analysis. NIPS 2006: 897-904 - 2005
- [j34]Aapo Hyvärinen:
Estimation of Non-Normalized Statistical Models by Score Matching. J. Mach. Learn. Res. 6: 695-709 (2005) - [j33]Fabrizio Esposito, Tommaso Scarabino, Aapo Hyvärinen, Johan Himberg, Elia Formisano, Silvia Comani, Gioacchino Tedeschi, Rainer Goebel, Erich Seifritz, Francesco Di Salle:
Independent component analysis of fMRI group studies by self-organizing clustering. NeuroImage 25(1): 193-205 (2005) - [j32]Aapo Hyvärinen:
A unifying model for blind separation of independent sources. Signal Process. 85(7): 1419-1427 (2005) - [c26]Shohei Shimizu, Aapo Hyvärinen, Yutaka Kano, Patrik O. Hoyer:
Discovery of Non-gaussian Linear Causal Models using ICA. UAI 2005: 525-533 - 2004
- [j31]Aapo Hyvärinen, Jarmo Hurri, Jaakko J. Väyrynen:
A unifying framework for natural image statistics: spatiotemporal activity bubbles. Neurocomputing 58-60: 801-806 (2004) - [j30]Jarmo Hurri, Jaakko J. Väyrynen, Aapo Hyvärinen:
Spatiotemporal receptive fields maximizing temporal coherence in natural image sequences. Neurocomputing 58-60: 815-820 (2004) - [j29]Johan Himberg, Aapo Hyvärinen, Fabrizio Esposito:
Validating the independent components of neuroimaging time series via clustering and visualization. NeuroImage 22(3): 1214-1222 (2004) - [j28]Aapo Hyvärinen, Jarmo Hurri:
Blind separation of sources that have spatiotemporal variance dependencies. Signal Process. 84(2): 247-254 (2004) - [c25]Jussi T. Lindgren, Aapo Hyvärinen:
Learning High-level Independent Components of Images through a Spectral Representation. ICPR (2) 2004: 72-75 - 2003
- [j27]Aapo Hyvärinen, Ella Bingham:
Connection between multilayer perceptrons and regression using independent component analysis. Neurocomputing 50: 211-222 (2003) - [j26]Jarmo Hurri, Aapo Hyvärinen:
A two-layer temporal generative model of natural video exhibits complex-cell-like pooling of simple cell outputs. Neurocomputing 52-54: 553-559 (2003) - [j25]Jarmo Hurri, Aapo Hyvärinen:
Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video. Neural Comput. 15(3): 663-691 (2003) - [j24]Vesa Kiviniemi, Juha-Heikki Kantola, Jukka Jauhiainen, Aapo Hyvärinen, Osmo Tervonen:
Independent component analysis of nondeterministic fMRI signal sources. NeuroImage 19(2): 253-260 (2003) - [c24]Johan Himberg, Aapo Hyvärinen:
Icasso: software for investigating the reliability of ICA estimates by clustering and visualization. NNSP 2003: 259-268 - 2002
- [j23]Patrik O. Hoyer, Aapo Hyvärinen:
Sparse coding of natural contours. Neurocomputing 44-46: 459-466 (2002) - [j22]Aapo Hyvärinen:
An alternative approach to infomax and independent component analysis. Neurocomputing 44-46: 1089-1097 (2002) - [j21]Shun-ichi Amari, Aapo Hyvärinen, Soo-Young Lee, Te-Won Lee, V. David Sánchez A.:
Blind signal separation and independent component analysis. Neurocomputing 49(1-4): 1-5 (2002) - [j20]Aapo Hyvärinen, Karthikesh Raju:
Imposing sparsity on the mixing matrix in independent component analysis. Neurocomputing 49(1-4): 151-162 (2002) - [j19]Aapo Hyvärinen, Mika Inki:
Estimating Overcomplete Independent Component Bases for Image Windows. J. Math. Imaging Vis. 17(2): 139-152 (2002) - [j18]Aapo Hyvärinen:
Realizations of quantum computing using optical manipulations of atoms. Nat. Comput. 1(2-3): 199-209 (2002) - [c23]Jarmo Hurri, Aapo Hyvärinen:
Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video. ICANN 2002: 33-38 - [c22]Jarmo Hurri, Aapo Hyvärinen:
Temporal Coherence, Natural Image Sequences, and the Visual Cortex. NIPS 2002: 141-148 - [c21]Patrik O. Hoyer, Aapo Hyvärinen:
Interpreting Neural Response Variability as Monte Carlo Sampling of the Posterior. NIPS 2002: 277-284 - 2001
- [b1]Aapo Hyvärinen, Juha Karhunen, Erkki Oja:
Independent Component Analysis. Wiley 2001, ISBN 0-471-40540-X, pp. 1-475 - [j17]Aapo Hyvärinen, Patrik O. Hoyer:
Topographic independent component analysis as a model of V1 organization and receptive fields. Neurocomputing 38-40: 1307-1315 (2001) - [j16]Aapo Hyvärinen:
Complexity Pursuit: Separating Interesting Components from Time Series. Neural Comput. 13(4): 883-898 (2001) - [j15]Aapo Hyvärinen, Patrik O. Hoyer, Mika Inki:
Topographic Independent Component Analysis. Neural Comput. 13(7): 1527-1558 (2001) - [j14]Aapo Hyvärinen:
Blind source separation by nonstationarity of variance: a cumulant-based approach. IEEE Trans. Neural Networks 12(6): 1471-1474 (2001) - 2000
- [j13]Ella Bingham, Aapo Hyvärinen:
A Fast Fixed-Point Algorithm for Independent Component Analysis of Complex Valued Signals. Int. J. Neural Syst. 10(1): 1-8 (2000) - [j12]Aapo Hyvärinen, Patrik O. Hoyer:
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces. Neural Comput. 12(7): 1705-1720 (2000) - [j11]Aapo Hyvärinen, Erkki Oja:
Independent component analysis: algorithms and applications. Neural Networks 13(4-5): 411-430 (2000) - [c20]Aapo Hyvärinen, Patrik O. Hoyer, Mika Inki:
Topographic ICA as a Model of Natural Image Statistics. Biologically Motivated Computer Vision 2000: 535-544 - [c19]Ella Bingham, Aapo Hyvärinen:
Fast and robust deflationary separation of complex valued signals. EUSIPCO 2000: 1-4 - [c18]Aapo Hyvärinen, Patrik O. Hoyer, Mika Inki:
Topographic ICA as a Model of V1 Receptive Fields. IJCNN (4) 2000: 83-88 - [c17]Ella Bingham, Aapo Hyvärinen:
ICA of Complex Valued Signals: A Fast and Robust Deflationary Algorithm. IJCNN (3) 2000: 357-362 - [c16]Patrik O. Hoyer, Aapo Hyvärinen:
Feature Extraction from Color and Stereo Images Using ICA. IJCNN (3) 2000: 369-376
1990 – 1999
- 1999
- [j10]Aapo Hyvärinen:
Sparse Code Shrinkage: Denoising of Nongaussian Data by Maximum Likelihood Estimation. Neural Comput. 11(7): 1739-1768 (1999) - [j9]Aapo Hyvärinen, Petteri Pajunen:
Nonlinear independent component analysis: Existence and uniqueness results. Neural Networks 12(3): 429-439 (1999) - [j8]Aapo Hyvärinen:
The Fixed-Point Algorithm and Maximum Likelihood Estimation for Independent Component Analysis. Neural Process. Lett. 10(1): 1-5 (1999) - [j7]Erkki Oja, Aapo Hyvärinen, Patrik O. Hoyer:
Image Feature Extraction and Denoising by Sparse Coding. Pattern Anal. Appl. 2(2): 104-110 (1999) - [j6]Aapo Hyvärinen:
Gaussian moments for noisy independent component analysis. IEEE Signal Process. Lett. 6(6): 145-147 (1999) - [j5]Aapo Hyvärinen:
Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Networks 10(3): 626-634 (1999) - [c15]Aapo Hyvärinen, Timo Honkela:
Emotional Disorders in Autonomous Agents? ECAL 1999: 350-354 - [c14]Aapo Hyvärinen, Razvan Cristescu, Erkki Oja:
A fast algorithm for estimating overcomplete ICA bases for image windows. IJCNN 1999: 894-899 - [c13]Aapo Hyvärinen, Patrik O. Hoyer:
Independent subspace analysis shows emergence of phase and shift invariant features from natural images. IJCNN 1999: 1059-1064 - [c12]Patrik O. Hoyer, Aapo Hyvärinen:
Estimating signal-adapted wavelets using sparseness criteria. IJCNN 1999: 2570-2575 - [c11]Aapo Hyvärinen:
Fast ICA for noisy data using Gaussian moments. ISCAS (5) 1999: 57-61 - [c10]Aapo Hyvärinen, Patrik O. Hoyer:
Emergence of Topography and Complex Cell Properties from Natural Images using Extensions of ICA. NIPS 1999: 827-833 - 1998
- [j4]Aapo Hyvärinen:
Independent component analysis in the presence of Gaussian noise by maximizing joint likelihood. Neurocomputing 22(1-3): 49-67 (1998) - [j3]Aapo Hyvärinen, Erkki Oja:
Independent component analysis by general nonlinear Hebbian-like learning rules. Signal Process. 64(3): 301-313 (1998) - [c9]Aapo Hyvärinen, Erkki Oja, Patrik O. Hoyer, Jarmo Hurri:
Image feature extraction by sparse coding and independent component analysis. ICPR 1998: 1268-1273 - [c8]Aapo Hyvärinen, Patrik O. Hoyer, Erkki Oja:
Sparse Code Shrinkage: Denoising by Nonlinear Maximum Likelihood Estimation. NIPS 1998: 473-479 - 1997
- [j2]Aapo Hyvärinen, Erkki Oja:
A Fast Fixed-Point Algorithm for Independent Component Analysis. Neural Comput. 9(7): 1483-1492 (1997) - [c7]Erkki Oja, Juha Karhunen, Aapo Hyvärinen:
From Neural Principal Components to Neural Independent Components. ICANN 1997: 519-528 - [c6]Juha Karhunen, Aapo Hyvärinen, Ricardo Vigário, Jarmo Hurri, Erkki Oja:
Applications of neural blind separation to signal and image processing. ICASSP 1997: 131-134 - [c5]Aapo Hyvärinen:
A family of fixed-point algorithms for independent component analysis. ICASSP 1997: 3917-3920 - [c4]Aapo Hyvärinen:
New Approximations of Differential Entropy for Independent Component Analysis and Projection Pursuit. NIPS 1997: 273-279 - 1996
- [j1]Aapo Hyvärinen, Erkki Oja:
Simple Neuron Models for Independent Component Analysis. Int. J. Neural Syst. 7(6): 671-688 (1996) - [c3]Aapo Hyvärinen:
Purely Logical Neural Principal Component and Independent Component Learning. ICANN 1996: 139-144 - [c2]Aapo Hyvärinen, Erkki Oja:
A neuron that learns to separate one signal from a mixture of independent sources. ICNN 1996: 62-67 - [c1]Aapo Hyvärinen, Erkki Oja:
One-unit Learning Rules for Independent Component Analysis. NIPS 1996: 480-486
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-19 21:46 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
