6.3 Current and Prior Applications of OpenCog 109 PROCEDURE EPISODIC BACKUP SERVER EMBEDDING REPOSITORY 4 MEMORY STORE SPACE ( REPOSITORY \ ) \ MAP | MBSES! “| worip sane — cute SIMULATION] |ENCoDING| | raeczinc, | 7 Bereta ENGINE / RECALL DEFROSTING | , ATTENTION ee es - 1’ |ALLOCATION \ | SEMANTIC ATOMS ty) ig —?@ 3) ) NEW ATOMS \ a / ba bd he ARE FORMED h co x HEBBIAN % @) ATOMS ARE \ ATOMS \ ‘ SELECTIVELY INFERENCE f \ PROCEDURE \ \ - fl ATOMS * | / | te \ , ox *—e ve * | ot ALL ATOMS | / ® @\| diatocuE Pal HAVE SHORT i; of Vo TAY PROCEDURE / o.- AND LONG-TERM | / 4 ATOMS x { i2? IMPORTANCE VALUES (| jf MOTOR i ¥ | / PROCEDURE ff *, | | / ATOMS a \\ ir Se ee ‘ \ \ + ” GOAL | @ FeeLinc \(CQ TRUTH VALUES \ \ \ e _ e ATOMS ‘, \ A oy an is one ATOM SPACE Sessa. \ , ——— rr | : a“ a PATTERN MINER. lan Ny fv \ Ls _ JTS fo Pa IMPRINTER = ~~ | Me ff Pa \ A Z# ] ——— ~ \ rr va 1 oor a ee Se ‘ \y es \ ff _ we \ | ay — \ oO \ 4 — | oo — oo — | — eT — ee PERCEPTION REINFORCEMENT, ACTION HIERARCHY, a | HIERARCHY a HIERARCHY LANGUAGE LANGUAGE COMPREHENSION GENERATION HERARCHY a se HIERARCHY, SENSORS ill ACTUATORS Fig. 6.1: High-Level Architecture of CogPrime. This is a conceptual depiction, not a detailed flowchart (which would be too complex for a single image). Figures 6.2 , 6.4 and 6.5 highlight specific aspects of this diagram. e Learning to build structures resembling structures that it’s shown (even if the available materials are a bit different) e Learning how to build bridges to cross chasms Of course, the AI significance of learning tasks like this all depends on what kind of feedback the system is given, and how complex its environment is. It would be relatively simple to make an AI system do things like this in a trivial and highly specialized way, but that is not the intent of the project the goal is to have the system learn to carry out tasks like this using general learning mechanisms and a general cognitive architecture, based on embodied experience and