Internal representations for associative memory

DOI10.1007/BF00332910MaRDI QIDQ1109556zbMATH OpenOpenAlexFDO

Authors S. H. Smith

Publication date 1988

Published in Biological Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf00332910

zbMATH Keywords

associative content addressable memoryfeed forward neural network modelsinternal label representations

Mathematics Subject Classification ID

Data structures (68P05) Learning and adaptive systems in artificial intelligence (68T05) Other natural sciences (mathematical treatment) (92F05)

Review text

We describe a class of feed forward neural network models for associative content addressable memory (ACAM) which utilize sparse internal representations for stored data. In addition to the input and output layers, our networks incorporate an intermediate processing layer which serves to label each stored memory and to perform error correction and association. We study two classes of internal label representations: the unary representation and various sparse, distributed representations. Finally, we consider storage of sparse data and sparsification of data. These models are found to have advantages in terms of storage capacity, hardware efficiency, and recall reliability when compared to the Hopfield model, and to possess analogies to both biological neural networks and standard digital computer memories.

Recommendations

• Sparse associative memory
• Storage capacities of sparse associative memories
• A comparative study of sparse associative memories
• Notions of associative memory and sparse coding
• Neural associative memory for brain modeling and information retrieval

Cites work

• An existence theory for pairwise balanced designs. III: Proof of the existence conjectures
• Content-addressable memories. 2nd ed
• scientific article; zbMATH DE number 3978900 (Why is no real title available?)
• scientific article; zbMATH DE number 3204545 (Why is no real title available?)
• Neural networks and physical systems with emergent collective computational abilities
• Neurons with graded response have collective computational properties like those of two-state neurons
• Self-organization and associative memory
• The Automatic Speech Recognition System for Conversational Sound
• The capacity of the Hopfield associative memory
• The existence of persistent states in the brain

Cited in

(14)

• On the capabilities of multilayer perceptrons
• Context-dependent associations in linear distributed memories
• Efficient retrieval from sparse associative memory
• A new neural network: Hybrid location-content addressable memory
• Generalized Hamming networks and applications
• A common network architecture efficiently implements a variety of sparsity-based inference problems
• KANERVA’S SPARSE DISTRIBUTED MEMORY: AN ASSOCIATIVE MEMORY ALGORITHM WELL-SUITED TO THE CONNECTION MACHINE
• scientific article; zbMATH DE number 3952572 (Why is no real title available?)
• scientific article; zbMATH DE number 4092809 (Why is no real title available?)
• Storage of linguistic information in a continuous classifying associative memory
• Short-term memory capacity in networks via the restricted isometry property
• Optimizing Potential Information Transfer with Self-referential Memory
• The evolution of internal representation
• Reduced order multiport parallel and multidirectional neural associative memories

This page was built for publication: Internal representations for associative memory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1109556)