Analysis of Linsker's simulations of Hebbian rules
Neural Computation
Understanding retinal color coding from first principles
Neural Computation
Learning factorial codes by predictability minimization
Neural Computation
What is the goal of sensory coding?
Neural Computation
An Information-Theoretic Approach to Neural Computing
An Information-Theoretic Approach to Neural Computing
Neural Computation
Feature extraction through LOCOCODE
Neural Computation
Neural networks with local receptive fields and superlinear VC Dimension
Neural Computation
Advances in evolutionary computing
Stacked convolutional auto-encoders for hierarchical feature extraction
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
On fast deep nets for AGI vision
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Flexible, high performance convolutional neural networks for image classification
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
| Hi-index | 0.00 |
Predictability minimization (PM---Schmidhuber 1992) exhibits various intuitive and theoretical advantages over many other methods for unsupervised redundancy reduction. So far, however, there have not been any serious practical applications of PM. In this paper, we apply semilinear PM to static real world images and find that without a teacher and without any significant preprocessing, the system automatically learns to generate distributed representations based on well-known feature detectors, such as orientation-sensitive edge detectors and off-center--on-surround detectors, thus extracting simple features related to those considered useful for image preprocessing and compression.