Statistical Prediction with Kanerva's Sparse Distributed Memory
نویسنده
چکیده
A new viewpoint of the processing performed by Kanerva's sparse distributed memory (SDM) is presented. In conditions of nearor overcapacity, where the associative-memory behavior of the model breaks down, the processing performed by the model can be interpreted as that of a statistical predictor. Mathematical results are presented which serve as the framework for a new statistical viewpoint of sparse distributed memory and for which the standard formulation of SDM is a special case. This viewpoint suggests possible enhancements to the SDM model, including a procedure for improving the predictiveness of the system based on Holland's work with 'Genetic Algorithms', and a method for improving the capacity of SDM even when used as an associative memory.
منابع مشابه
Statistical Sparse Distributed Memory Prediction with Kanerva's
A new viewpoint of the processing: performed by Kanerva's sparse distributed memory (SDM) is presented. In conditions of nearor overcapacity, where the associative-memory behavior of the model breaks down, the processing performed by the model can be interpreted as that of a statistical predictor. Mathematical results are presented which serve as the framework for a new statistical viewpoint of...
متن کاملKanerva's Sparse Distributed Memory with Multiple Hamming Thresholds
If the stored input patterns of Kanerva's Sparse Distributed Memory (SDM) are highly correlated, utilization of the storage capacity is very low compared to the case of uniformly distributed random input patterns. Here we consider a variation of SDM that has a better storage capacity utilization for correlated input patterns. This approach uses a separate selection threshold for each physical s...
متن کاملPredicting Weather Using a Genetic Memory: A Combination of Kanerva's Sparse Distributed Memory with Holland's Genetic Algorithms
Kanerva's sparse distributed memory (SDM) is an associative-memory model based on the mathematical properties of high-dimensional binary address spaces. Holland's genetic algorithms are a search technique for high-dimensional spaces inspired by evolutionary processes of DNA. "Genetic Memory" is a hybrid of the above two systems, in which the memory uses a genetic algorithm to dynamically reconf...
متن کاملKanerva's Sparse Distributed Memory: An Object-Oriented Implementation on the Connection Machine
This paper reports on an implementation of Kanerva's Sparse Distributed Memory for the Connection Machine. In order to accomplish a modular and adaptive software library we applied a plain object-oriented programming style to the Common Lisp extension *ltsp. Some variations of the original model, the selected coordinate design, the hyperplane design, and a new general design, as well as the fol...
متن کاملBest Probability of Activation and Performance Comparisons for Several Designs of Sparse Distributed Memory
The optimal probability of activation and the corresponding performance is studied for three designs of Sparse Distributed Memory, namely, Kanerva's original design, Jaeckel's selected-coordinates design and Karlsson's modification of Jaeckel's design. We will assume that the hard locations (in Karlsson's case, the masks), the storage addresses and the stored data are randomly chosen, and we wi...
متن کامل