Energy function for learning invariance in multilayerperceptron
- 5 February 1998
- journal article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 34 (3) , 292-294
- https://doi.org/10.1049/el:19980161
Abstract
A new energy function is proposed for forming self-adapting ordered representations of input samples in a multilayer perceptron. Simulation results on unconstrained handwritten digit recognition give a better invariance extraction for this model than for several other models.Keywords
This publication has 4 references indexed in Scilit:
- Optimal, Unsupervised Learning in Invariant Object RecognitionNeural Computation, 1997
- Using Spatio-temporal Correlations to Learn Invariant Object RecognitionNeural Networks, 1996
- Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature, 1996
- Learning Invariance from Transformation SequencesNeural Computation, 1991