Similarity-based reasoning with ensemble memory voting

A method for recognizing an analogous case from a knowledge base including a plurality of candidate cases, the method comprising:

• receiving a representation of a target case;
• extracting a plurality of target attributes from the representation of the target case;
• querying the knowledge base to recognize the analogous case similar to the target case in information content using (1) the target attributes and (2) a plurality of attribute memories each including first and second attributes and an inter-attribute contextual representation of interactions between the first and second attributes in a context of the plurality of candidate cases;
• and
• presenting the recognized analogous case to a user or a process.

At least one machine readable storage medium, comprising a plurality of instructions that, responsive to being executed with processor circuitry of a computing device, cause the computing device to:

• receive a representation of a target case;
• generate a plurality of target attributes from the representation of the target case;
• query a knowledge base including a plurality of candidate cases to recognize the analogous case similar to the target case in information content using (1) the target attributes and (2) a plurality of attribute memories each including first and second attributes and an inter-attribute contextual representation of interactions between the first and second attributes in a context of the plurality of candidate cases;
• and
• present the recognized analogous case to a user or a process.