Online learning and generalization of parts-based image representations by non-negative sparse autoencoders
We present an efficient online learning scheme for non-negative sparse coding in
autoencoder neural networks. It comprises a novel synaptic decay rule that ensures non …
autoencoder neural networks. It comprises a novel synaptic decay rule that ensures non …
Multidimensional hebbian learning with temporal coding in neocognitron visual recognition
YP Lee - IEEE Transactions on Systems, Man, and Cybernetics …, 2016 - ieeexplore.ieee.org
Previous work on Fuskushima's neocognitron neural network model has mostly focused on
binary character recognition, but grayscale images are preferable to binary images in real …
binary character recognition, but grayscale images are preferable to binary images in real …
[PDF][PDF] Hierarchical feed-forward models for robust object recognition
I Bax - 2007 - core.ac.uk
Hierarchical Feed-Forward Models for Robust Object Recognition Ingo Bax Page 1 Hierarchical
Feed-Forward Models for Robust Object Recognition Ingo Bax Der Technischen Fakultät der …
Feed-Forward Models for Robust Object Recognition Ingo Bax Der Technischen Fakultät der …