• Corpus ID: 17547390

Integer Sparse Distributed Memory

  title={Integer Sparse Distributed Memory},
  author={Javier Snaider and Stan Franklin},
  booktitle={FLAIRS Conference},
Sparse distributed memory is an auto-associative me mory system that stores high dimensional Boolean vectors . Here we present an extension of the original SDM, the In t ger SDM that uses modular arithmetic integer vectors ra ther than binary vectors. This extension preserves many of the desirable properties of the original SDM: auto-asso ciativity, content addressability, distributed storage, and ro bustness over noisy inputs. In addition, it improves the rep resentation capabilities of the… 

Figures from this paper

Integer Sparse Distributed Memory Based on Neural Coding

  • Xiaowei WangH. Meng
  • Computer Science
    Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery
  • 2021
A biologically plausible encoding scheme to enableparse Distributed Memory to accept integer vectors, requiring much less space than the existing integer SDM model is proposed.

Modular Composite Representation

This work introduces the modular composite representation (MCR), a new reduced description model that employs long integer vectors and gives a theoretical analysis of the distance distribution in this vector space, and of properties of this representation.

A Radically New Theory of how the Brain Represents and Computes with Probabilities

Simulation results are provided showing that the active SDC simultaneously represents not only the spatially/spatiotemporally most similar/likely input but the coarsely-ranked similarity/likelihood distribution over all stored inputs (hypotheses).

Spatial Working Memory in the LIDA Cognitive Architecture

A biologically inspired computational model of spatial working memory attempting to account for properties of human spatial representations, based on the LIDA cognitive architecture is described.

Cognitive Machine-Learning Algorithm for Cardiac Imaging: A Pilot Study for Differentiating Constrictive Pericarditis From Restrictive Cardiomyopathy.

Feasibility of a cognitive machine-learning approach for learning and recalling patterns observed during echocardiographic evaluations is demonstrated, which may aid standardized assessments and support the quality of interpretations of interpretations.



Extended Sparse Distributed Memory and Sequence Storage

This work presents an extension of the original SDM that uses word vectors of larger size than address vectors, enabling an efficient auto-associative storage of sequences of vectors, as well as of other data structures such as trees.

Assessing a Sparse Distributed Memory Using Different Encoding Methods

This project intends to navigate a robot using a sparse distributed memory to store sequences of sensorial information, and tested different methods of encoding the data, finding some perform better than others, though some may fade particular characteristics present in the original.

An alternative design for a sparse distributed memory

A new design for a Sparse Distributed Memory, called the selected-coordinate design, is described. As in the original design, there are a large number of memory locations, each of which may be

Realizing Forgetting in a Modified Sparse Distributed Memory System

Realizing Forgetting in a Modified Sparse Distributed Memory System Uma Ramamurthy (urmmrthy@memphis.edu) Sidney K. D’Mello (sdmello@memphis.edu) Stan Franklin (franklin@memphis.edu) Computer Science

A class of designs for a sparse distributed memory

A general class of designs for a space distributed memory (SDM) is described. The author shows that Kanerva's original design and the selected-coordinate design are related, and that there is a

Sparse Distributed Memory

Pentti Kanerva's Sparse Distributed Memory presents a mathematically elegant theory of human long term memory that resembles the cortex of the cerebellum, and provides an overall perspective on neural systems.

Encoding and Retrieval Efficiency of Episodic Data in a Modified Sparse Distributed Memory System

A modified SDM architecture is presented that promises to be a good candidate for use as a TEM in software agents such as IDA, and it is hypothesized that information stored in TEM, which has not decayed away, is consolidated into declarative memory at certain intervals.

Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors

  • P. Kanerva
  • Computer Science
    Cognitive Computation
  • 2009
The thesis of the paper is that hyperdimensional representation has much to offer to students of cognitive science, theoretical neuroscience, computer science and engineering, and mathematics.

The Role of Consciousness in Memory

Conscious events interact with memory systems in learning, rehearsal and retrieval (Ebbinghaus 1885/1964; Tulving 1985). Here we present hypotheses that arise from the IDA computional model

Memory Systems for Cognitive Agents

The various memory systems in the LIDA Architecture, which implements Global Workspace Theory, are described and the interaction between these memory systems, feelings and emotions, and consciousness in the context of cognitive cycles are discussed.