Hebbian learning and competition in the neural abstraction pyramid

By Sven Behnke. 1999

How researchers see this paper

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

1. Klaus Greff
2. J. Urgen Schmidhuber
3. Yoshua Bengio
4. Sjoerd van Steenkiste
5. Sergey Levine
6. Andrea Vedaldi
7. Quoc V. Le
8. Kyunghyun Cho

Citations in the corpus

• Tagger: Deep Unsupervised Perceptual Grouping (2016, background): “therefore in principle be learned by any RNN as a by-product of data compression or any other given task. The recurrent architecture most similar to the Tagger is the Neural Abstraction Pyramid (NAP; [3]) – a convolutional neural network augmented with lateral connections which help resolve local am”
• Discovering hierarchical speech features using convolutional non-negative matrix factorization (2003, methodology): “For images, such hierarchical models have been discovered by unsupervised learning techniques and successfully used for object recognition tasks in the Neural Abstraction Pyramid architecture [8], [9].”
• Learning Optimized Features for Hierarchical Models of Invariant Object Recognition (2003, methodology): “Behnke (1999) applied a Hebbian learning approach with competitive activity normalizations to the unsupervised learning of hierarchical visual features for digit recognition.”