Hiroshi Morioka

Code

Matlab code for Common Dictionary Learning

The code was used to perform the experiments in the paper

Morioka, H., Kanemura, A., Hirayama, J., Shikauchi, M., Ogawa, T., Ikeda, S., Kawanabe, M., Ishii, S. Learning a common dictionary for subject-transfer decoding with resting calibration. NeuroImage. Vol. 111, pp. 167—178, 2015.

If you are using pieces of the posted code, please cite the above paper.

Also check EEG database (Open-access ATR Network-BMI Brain Database) used in the paper.

Python code for Time-Contrastive Learning (TCL)

The code was used to perform the simulations in the paper

Hyvarinen, A., Morioka, H., Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA. In Advances in Neural Information Processing Systems (NIPS2016), pp. 3765–3773. Barcelona, Dec. 2016.

If you are using pieces of the posted code, please cite the above paper.

Python code for Permutation-Contrastive Learning (PCL)

The code was used to perform the simulations in the paper

Hyvarinen, A., Morioka, H., Nonlinear ICA of Temporally Dependent Stationary Sources, AISTATS 2017.

If you are using pieces of the posted code, please cite the above paper.

Python code for Independent-Innovation Analysis (IIA)

The code was used to perform the simulations in the paper

Morioka, H., Hälvä, H., and Hyvärinen, A. Independent innovation analysis for nonlinear vector autoregressive process. AISTATS 2021.

If you are using pieces of the posted code, please cite the above paper.

Python code for Connectivity-Contrastive Learning (CCL)

The code was used to perform the simulations in the paper

Morioka, H. and Hyvärinen, A. Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data. AISTATS 2023.

If you are using pieces of the posted code, please cite the above paper.

Python code for Grouped Causal Representation Learning (G-CaRL)

The code was used to perform the simulations in the paper

Morioka, H. and Hyvärinen, A. Causal Representation Learning Made Identifiable by Grouping of Observational Variables. ICML 2024.

If you are using pieces of the posted code, please cite the above paper.

Google Sites

Report abuse