Fetching the paper…
Reading the bibliography…
We introduce a new framework for unsupervised learning of representations based on a novel hierarchical decomposition of information.
A mathematical theory of communication
Shannon, C.E · 1948
Earlier work this paper cites.
A method for the construction of minimum redundancy codes
Huffman, David A et al · 1952
Earlier work this paper cites.
Information theoretical analysis of multivariate correlation
Watanabe, Satosi · 1960
Earlier work this paper cites.
A universal algorithm for sequential data compression
Ziv, Jacob and Lempel, Abraham · 1977
Earlier work this paper cites.
Self-organization in a perceptual network
Linsker, Ralph · 1988
Earlier work this paper cites.
Unsupervised learning
Barlow, Horace · 1989
Earlier work this paper cites.
Independent component analysis, a new concept?
Comon, Pierre · 1994
Earlier work this paper cites.
An information-maximization approach to blind separation and blind deconvolution
Bell, Anthony J and Sejnowski, Terrence J · 1995
Earlier work this paper cites.
Feature extraction through lococode
Hochreiter, Sepp and Schmidhuber, Jürgen · 1999
Earlier work this paper cites.
Independent component analysis: algorithms and applications
Hyvärinen, Aapo and Oja, Erkki · 2000
Earlier work this paper cites.
The information bottleneck method
Tishby, Naftali, Pereira, Fernando C, and Bialek, William · 2000
Earlier work this paper cites.
Information geometry on hierarchy of probability distributions
Amari, Shun-ichi · 2001
Cited alongside, same era.
Natural image statistics and neural representation
Simoncelli, Eero and Olshausen, Bruno · 2001
Cited alongside, same era.
Least-dependent-component analysis based on mutual information
Stögbauer, Harald, Kraskov, Alexander, Astakhov, Sergey A, and Grassberger, Peter · 2004
Cited alongside, same era.
Hierarchical clustering using mutual information
Kraskov, Alexander, Stögbauer, Harald, Andrzejak, Ralph G, and Grassberger, Peter · 2005
Cited alongside, same era.
Elements of information theory
Cover, Thomas M and Thomas, Joy A · 2006
Cited alongside, same era.
Reducing the dimensionality of data with neural networks
Hinton, Geoffrey E and Salakhutdinov, Ruslan R · 2006
Cited alongside, same era.
Generalized binary independent component analysis
Painsky, Amichai, Rosset, Saharon, and Feder, Meir · 2014
Later among the works it cites.
Discovering structure in high-dimensional data through correlation explanation
Ver Steeg, Greg and Galstyan, Aram · 2014
Later among the works it cites.
Demystifying information-theoretic clustering
Ver Steeg, Greg, Galstyan, Aram, Sha, Fei, and DeDeo, Simon · 2014
Later among the works it cites.
Deep learning in neural networks: An overview
Schmidhuber, Jürgen · 2015
Closest in time.
Information-theoretic inference of common ancestors
Steudel, Bastian and Ay, Nihat · 2015
Closest in time.
Deep learning and the information bottleneck principle
Tishby, Naftali and Zaslavsky, Noga · 2015
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Extracting and composing robust features with denoising autoencoders
Vincent, Pascal, Larochelle, Hugo, Bengio, Yoshua, and Manzagol, Pierre-Antoine · 2008
Cited alongside, same era.
Nonnegative decomposition of multivariate information
Williams, P.L. and Beer, R.D · 2010
Cited alongside, same era.
Learning representations by maximizing compression
Gregor, Karol and LeCun, Yann · 2011
Cited alongside, same era.
Representation learning: A review and new perspectives
Bengio, Yoshua, Courville, Aaron, and Vincent, Pascal · 2013
Cited alongside, same era.
Open source project implementing the discrete information sieve
Ver Steeg, Greg
Cited in the paper.
Closest in time.
Maximally informative hierarchical representations of high-dimensional data
Ver Steeg, Greg and Galstyan, Aram · 2015
Closest in time.
Relative value of diverse brain mri and blood-based biomarkers for predicting cognitive decline in the elderly
Madsen, Sarah, Ver Steeg, Greg, Daianu, Madelaine, Mezher, Adam, Jahanshad, Neda, Nir, Talia M., Hua, Xue, Gutman, Boris A., Galstyan, Aram, and Thompson, Paul M · 2016
Closest in time.
Multivariate information maximization yields hierarchies of expression components in tumors that are both biologically meaningful and prognostic
Pepke, Shirley and Ver Steeg, Greg · 2016
Closest in time.
Sifting common information from many variables
Ver Steeg, Greg, Gao, Shuyang, Reing, Kyle, and Galstyan, Aram · 2016
Closest in time.