Comparison of two Unsupervised Neural Network Models for Redundancy Reduction

By Stefanie N. Lindstaedt. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep learning in neural networks: An overview (2014, background): “e detectors that ﬁght nonlinear predictors, trying to become both as informative and as unpredictable as possible. PM-based UL was applied not only to FNNs but also to RNNs (e.g., Schmidhuber, 1993b; Lindstadt, 1993a,b). Compare Sec. 5.10 on UL-based RNN stacks (1991), as well as later UL¨ RNNs (e.g”
Sequential neural text compression (1996, methodology): “See [6] for a method that uses predictors of conditional probabilities to develop factorial codes of environmental input patterns { codes with the property that the code components are statistically independent (see [9] and [3] for applications).”
Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams (2012, background): “Other UL systems that both learn and apply features to sequences (Schmidhuber, 1992a,c,b; Lindstädt, 1993; KlapperRybicka et al., 2001; Jenkins and Matarić, 2004; Lee et al., 2010; Gisslen et al., 2011), thus assuming that the state of the system itself can depend on past information.”
Semilinear Predictability Minimization Produces Well-Known Feature Detectors (1996, methodology): “Despite its potential advantages, PM has been tested on artificial data only (Lindstadt 1993; Schmidhuber 1993, 1994).”