𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Forming sparse representations by local anti-Hebbian learning

✍ Scribed by P. Földiák

Book ID
105536104
Publisher
Springer-Verlag
Year
1990
Tongue
English
Weight
560 KB
Volume
64
Category
Article
ISSN
0340-1200

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Improved bidirectional retrieval of spar
Improved bidirectional retrieval of sparse patterns stored by Hebbian learning
✍ Friedrich T. Sommer; Günther Palm 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 288 KB

The Willshaw model is asymptotically the most efficient neural associative memory (NAM), but its finite version is hampered by high retrieval errors. Iterative retrieval has been proposed in a large number of different models to improve performance in auto-association tasks. In this paper, bidirecti

ORASSYLL: Object Recognition with Autono
ORASSYLL: Object Recognition with Autonomously Learned and Sparse Symbolic Representations Based on Metrically Organized Local Line Detectors
✍ Norbert Krüger; Gabriele Peters 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 565 KB

We introduce an object recognition and localization system in which objects are represented as a sparse and spatially organized set of local (bent) line segments. The line segments correspond to binarized Gabor wavelets or banana wavelets, which are bent and stretched Gabor wavelets. These features