Modeling Grouping with Recursive Auto-Associative Memory
نویسندگان
چکیده
Sometimes humans have a need for storing long sequences of information in memory. Several experiments show that grouping the items in the sequence helps storing the sequence in auditory short-term memory. One architecture used by connectionist cognitive researchers when representing and processing sequences is Recursive Auto-Associative Memory. One of the aspects of it is that its capacity for storing sequences is limited, leading to that the longer the sequence the less likely it is that the entire sequence can be recalled; the deepest parts of the sequence are forgotten. Two experiments are performed to test if grouping affects storage in Recursive Auto-Associative Memories. We conclude that grouping affects the ability for storing sequences in Recursive AutoAssociative Memories much in the same way as it affects the human auditory short-term memory, i.e., using grouping increase the probability of that the sequence can be recalled correctly.
منابع مشابه
Connectionist rule processing using recursive auto-associative memory
A limitation of many rule-based connectionist models is their dependence on structure to explicitly represent rules, and their consequent inflexibility in acquiring and applying novel rules. A model is described in which recursive auto-associative memory (RAAM) is used as an encoding mechanism to prepare rules of variable structure and content for input to a connectionist rule applicator. The e...
متن کاملRecursive Hetero-associative Memories for Translation
This paper presents a modiication of Pollack's RAAM (Re-cursive Auto-Associative Memory), called a Recursive Hetero-Associative Memory (RHAM), and shows that it is capable of learning simple translation tasks, by building a state-space representation of each input string and unfolding it to obtain the corresponding output string. RHAM-based translators are computationally more powerful and easi...
متن کاملA Neural Network-Based Cryptographic System
We present a cryptographic system based on Pollack’s recursive auto-associative memory (1991). This self-organizing learning system offers many unique properties not found in traditional crypto systems. This paper examines the methodology and issues of such a system.
متن کاملEvaluation of Two Connectionist Approaches toStack
This study empirically compares two distributed connectionist learning models trained to represent an arbitrarily deep stack. One is Pol-lack's Recursive Auto-Associative Memory, a recurrent back propagating neural network that uses a hidden intermediate representation. The other is the Exponential Decay Model, a novel architecture that we propose here, which tries to learn an explicit represen...
متن کاملEvaluation of Two Connectionist Approaches to Stack Representation
This study empirically compares two distributed connectionist learning models trained to represent an arbitrarily deep stack. One is Pol-lack's Recursive Auto-Associative Memory, a recurrent back propagating neural network that uses a hidden intermediate representation. The other is the Exponential Decay Model, a novel architecture that we propose here, which tries to learn an explicit represen...
متن کامل