HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Linear Recursive Distributed Representations

Thomas Voegtlin 1 Peter Dominey 2
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Connectionist networks have been criticized for their inability to represent complex structures with systematicity. That is, while they can be trained to represent and manipulate complex objects made of several constituents, they generally fail to generalize to novel combinations of the same constituents. This paper presents a modification of Pollack's Recursive Auto-Associative Memory (RAAM), that addresses this criticism. The network uses linear units and is trained with Oja's rule, in which it generalizes PCA to tree-structured data. Learned representations may be linearly combined, in order to represent new complex structures. This results in unprecedented generalization capabilities. Capacity is orders of magnitude higher than that of a RAAM trained with back-propagation. Moreover, regularities of the training set are preserved in the new formed objects. The formation of new structures displays developmental effects similar to those observed in children when learning to generalize about the argument structure of verbs.
Document type :
Journal articles
Complete list of metadata

Contributor : Thomas Voegtlin Connect in order to contact the contributor
Submitted on : Monday, June 13, 2005 - 2:25:27 PM
Last modification on : Friday, February 4, 2022 - 3:16:03 AM
Long-term archiving on: : Thursday, April 1, 2010 - 9:40:38 PM



  • HAL Id : inria-00000108, version 1



Thomas Voegtlin, Peter Dominey. Linear Recursive Distributed Representations. Neural Networks, Elsevier, 2005, 18 (7), pp.878-895. ⟨inria-00000108⟩



Record views


Files downloads