Nonlinear Independent Component Analysis
[Very recently we have developed a new framework for a nonlinear version of ICA, which is a principled approach to unsupervised deep learning.]
A. Hyvärinen and H. Morioka.
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA.
NIPS 2016.
pdf
[A new method for nonlinear ICA, based on the temporal structure of the independent components. Unlike in previous approaches, we can actually prove that the method recovers the independent components, i.e. it is identifiable.]
A. Hyvärinen and H. Morioka.
Nonlinear ICA of Temporally Dependent Stationary Sources.
AISTATS 2017.
pdf
[A second method for identifiable nonlinear ICA with different assumptions of the temporal structure of the components.]
J. Hirayama, A. Hyvärinen and M. Kawanabe.
SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling.
ICML 2017.
pdf
[A hierarchical extension of ICA and ISA, emphasizing pooling and modelling V2 for example. The model is tractable from an estimation viewpoint, which was earlier believed to be impossible.]
A. Hyvärinen and P. Pajunen. Nonlinear Independent Component Analysis:
Existence and Uniqueness results. Neural Networks 12(3): 429--439, 1999.
pdf
[Older work showing that the solution of the nonlinear ICA problem is highly non-unique if the data has no temporal structure. Here we further propose an identifiable version by strongly restricting the nonlinearity.]
|
