An Autoassociative Neural Network Model of Paired-Associate Learning
Authors:
- 1 September 2001
- journal article
- Published by MIT Press in Neural Computation
- Vol. 13 (9) , 2075-2092
Abstract
Hebbian heteroassociative learning is inherently asymmetric. Storing a forward association, from item A to item B, enables recall of B (given A), but does not permit recall of A (given B). Recurrent networks can solve this problem by associating A to B and B back to A. In these recurrent networks, the forward and backward associations can be differentially weighted to account for asymmetries in recall performance. In the special case of equal strength forward and backward weights, these recurrent networks can be modeled as a single autoassociative network where A and B are two parts of a single, stored pattern. We analyze a general, recurrent neural network model of associative memory and examine its ability to fit a rich set of experimental data on human associative learning. The model fits the data significantly better when the forward and backward storage strengths are highly correlated than when they are less correlated. This network-based analysis of associative learning supports the view that associations between symbolic elements are better conceptualized as a blending of two ideas into a single unit than as separately modifiable forward and backward associations linking representations in memory.Keywords
This publication has 33 references indexed in Scilit:
- Slow stochastic Hebbian learning of classes of stimuli in a recurrent neural networkNetwork: Computation in Neural Systems, 1998
- Conservation of hippocampal memory function in rats and humansNature, 1996
- Learning internal representations in an attractor neural network with analogue neuronsNetwork: Computation in Neural Systems, 1995
- Mathematical and Connectionist Models of Human Memory: A ComparisonMemory, 1995
- Onset and stabilization of NMDA receptor-dependent hippocampal long-term potentiationNeuroscience Research, 1994
- Normal and amnesic learning, recognition and memory by a neural model of cortico-hippocampal interactionsTrends in Neurosciences, 1993
- Constraints on learning in dynamic synapsesNetwork: Computation in Neural Systems, 1992
- Associative memory with high information contentPhysical Review A, 1989
- A simple neural network generating an interactive memoryMathematical Biosciences, 1972
- Backward associations.Psychological Bulletin, 1966