ICA-Based binary feature construction

Authors:
Ata Kabán;Ella Bingham
Affiliations:
School of Computer Science, The University of Birmingham, Birmingham, UK;HIIT BRU, University of Helsinki, Finland
Venue:
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Year:
2006

Citing 3
Cited 1

Probabilistic visualisation of high-dimensional binary data

Proceedings of the 1998 conference on Advances in neural information processing systems II
Latent dirichlet allocation

The Journal of Machine Learning Research
Applying discrete PCA in data analysis

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence

Factorisation and denoising of 0-1 data: A variational approach

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of interactive feature construction and denoising of binary data. To this end, we develop a variational ICA method, employing a multivariate Bernoulli likelihood and independent Beta source densities. We relate this to other binary data models, demonstrating its advantages in two application domains.