Abstract
Although the detection of invariant structure in a given set of input patterns is vital to many recognition tasks, connectionist learning rules tend to focus on directions of high variance (principal components). The prediction paradigm is often used to reconcile this dichotomy; here we suggest a more direct approach to invariant learning based on an anti-Hebbian learning rule. An unsupervised two-layer network implementing this method in a competitive setting learns to extract coherent depth information from random-dot stereograms.
Keywords
Hebbian theoryCompetitive learningConnectionismComputer scienceArtificial intelligenceUnsupervised learningLeabraInvariant (physics)Set (abstract data type)Variance (accounting)Focus (optics)Feature learningArtificial neural networkMachine learningPattern recognition (psychology)MathematicsGeneralization errorWake-sleep algorithm
Affiliated Institutions
Related Publications
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether...
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly...
Publication Info
- Year
- 1991
- Type
- article
- Volume
- 4
- Pages
- 1017-1024
- Citations
- 26
- Access
- Closed
External Links
Citation Metrics
26
OpenAlex
Cite This
Nicol N. Schraudolph,
Terrence J. Sejnowski
(1991).
Competitive Anti-Hebbian Learning of Invariants.
, 4
, 1017-1024.