Systematicity in sentence processing with a recursive self-organizing neural network

Abstract. As potential candidates for human cognition, connectionist models of sentence processing must learn to behave systematically by generalizing from a small traning set. It was recently shown that Elman networks and, to a greater extent, echo state networks (ESN) possess limited ability to generalize in artificial language learning tasks. We study this capacity for the recently introduced recursive self-organizing neural network model and show that its performance is comparable with ESNs.

• Type: Conference
• Year: 2007
• Where: ESANN
• Authors: Igor Farkas, Matthew W. Crocker
• Keywords: Echo State Networks, ESANN 2007, Neural Networks, Possess Limited Ability, Self-organizing Neural Network