US 9,002,762 B1 · System and method for adaptive recall

Abstract

Described is a system for adaptive memory recall. The system receives original input data, then divides the original input data into multiple data groups to serve as input for a network comprising a pattern separation layer and an autoassociative memory layer. The original input data is processed with a pattern separation component of the pattern separation layer, and each pattern separation component generates an increased-contrast version of the original input data it processes. The generated increased-contrast version of the original input data is combined with the original input data and stored in an autoassociative memory component of the autoassociative memory layer for each data group. New input data is received, and a parameter that controls processing in the pattern separation layer is modulated to determine an optimal parameter, which indicates that a memory recall between the stored data and the new set of input data is achieved.

Claims21

Dependent claims

A system for adaptive memory recall, the system comprising:

one or more processors and a memory having instructions such that when the instructions are executed, the one or more processors perform operations of:
receiving a set of original input data;
dividing the set of original input data into a plurality of data groups to serve as input for a network comprising a pattern separation layer and an autoassociative memory layer, wherein the pattern separation layer comprises a plurality of pattern separation components and the autoassociative memory layer comprises a plurality of autoassociative memory components;
for each data group, processing of the original input data with a distinct pattern separation component of the pattern separation layer, wherein each pattern separation component generates an increased-contrast version of the original input data it processes;
for each data group, combining the generated increased-contrast version of the original input data from the pattern separation layer with the original input data, resulting in combined input data;
and
for each data group, storing the combined input data in a distinct autoassociative memory component, resulting in stored data.

4 more elements

A computer-implemented method for adaptive memory recall, comprising:

an act of causing a data processor to execute instructions stored on a non-transitory memory such that upon execution, the data processor performs operations of:
receiving a set of original input data;
dividing the set of original input data into a plurality of data groups to serve as input for a network comprising a pattern separation layer and an autoassociative memory layer, wherein the pattern separation layer comprises a plurality of pattern separation components and the autoassociative memory layer comprises a plurality of autoassociative memory components;
for each data group, processing of the original input data with a distinct pattern separation component of the pattern separation layer, wherein each pattern separation component generates an increased-contrast version of the original input data it processes;
for each data group, combining the generated increased-contrast version of the original input data from the pattern separation layer with the original input data, resulting in combined input data;
and
for each data group, storing the combined input data in a distinct autoassociative memory component, resulting in stored data.

4 more elements

A computer program product for adaptive memory recall, the computer program product comprising instructions stored on a non-transitory computer-readable medium that are executable by a computer having a processor for causing the processor to perform operations of:

receiving a set of original input data;
dividing the set of original input data into a plurality of data groups to serve as input for a network comprising a pattern separation layer and an autoassociative memory layer, wherein the pattern separation layer comprises a plurality of pattern separation components and the autoassociative memory layer comprises a plurality of autoassociative memory components;
for each data group, processing of the original input data with a distinct pattern separation component of the pattern separation layer, wherein each pattern separation component generates an increased-contrast version of the original input data it processes;
for each data group, combining the generated increased-contrast version of the original input data from the pattern separation layer with the original input data, resulting in combined input data;
and
for each data group, storing the combined input data in a distinct autoassociative memory component, resulting in stored data.

3 more elements

Dependencies are inferred from the claim text.

System and method for adaptive recall

Life of this patent

System and method for adaptive recall

Life of this patent

Abstract

Claims21