Epstein Secrets

r the latter are learned via MOSES or via some other means. The textual realization of Combo resembles LISP with less syntactic sugar. Internally a Combo program is represented as a program tree. • Composer: In the PLN design, a rule is denoted a composer if it needs premises for generating its conse

ve its fingers to pick up a cup, coordinating its movements with its visual perceptions. It's certainly possible to represent this sort of thing in Combo, but Combo may be an awkward tool. However, if one represents low-level procedures like this using another method, e.g. learned cell assemblies in a

the question of programs in what programming language, and in this context we have made a fairly traditional choice, using a special language called Combo that is essentially a minor variant of LISP, and supplying Combo with a set of customized primitives intended to reduce the length of the typical p

. • Imitation Learning: Learning via copying what some other agent is observed to do. • Implication: Often refers to an ImplicationLink between two PredicateNodes, indicating an (extensional, intensional or mixed) logical implication. • Implicit Knowledge Representation: Representation of knowledge via having

its own hardware and software infrastructure. CogPrime represents procedures as programs in an internal programming language called "Combo." While Combo has a textual representation, described online at the OpenCog wiki, this isn't one of its more important aspects (and may be redesigned slightly or

an internal node of a program, can also live in its own Atom. For example. a number in a program tree corresponds to a NmnberNode; an argument in a Combo program already corresponds to some Atom; and an operator in a program can be wrapped up in a Schemallode all its own, and considered as a one-leaf

entioned: 1. Via preprocessing of perceptual inputs (e.g. the names of NumberNode, CharacterNodes) 2. Via hard-wiring of names for Schemallodes and PredicateNodes corresponding to built-in elementary schema (e.g. +, AND, Say) If an Atom A has a name n in the system, we may write A.name n On the other hand,

tricks, fetch_ball and triple_kick to be described below. in order to calibrate the size penalty function: 1. fetch_ball, which corresponds to the Combo program and_seg (goto (ball) grab (ball) goto (owner) drop) 2. triple_kick, if the stick is near the ball then kick 3 times with the left leg an

n x, two possibilities exist: EFTA00624385 33.6 Hierarchical Program Learning 239 • There is already a model for PredicateNodes at position x in Combo trees in the given population, in which case a population of PredicateNodes potentially living at that position is drawn from the known model, and

specification PredicateNode as true as possible). In evolutionary computing lingo, the specification predicate is a fitness function. Searching for PredicateNodes that embody patterns in the AtomSpace as a whole is a spe- cial case of this kind of learning, where the specification PredicateNode embodies a notio

uesses produced by pure procedure learning methods), it may still be valuable to have this procedure in compact and rapidly executable form such as Combo provides. To proceed with the technical description of predicate schematization in CogPrime. we first need the notion of an "executable predicate".

tand: all else equal, a predicate embodied in a small Combo tree is better than a predicate embodied in a big one. There is some work hidden here in Combo tree reduction; ideally, one would like to find the smallest representation of a given Combo tree, but this is a computationally formidable problem

subgraphs containing Atom-valued variables . Each such subgraph may be represented as a PredicateNode, and frequent subgraph mining will find such PredicateNodes that have surprisingly high truth values when evaluated across the Atomspace. But unlike MOSES when applied as described above, such an algorithm wi

r the latter are learned via MOSES or via some other means. The textual realization of Combo resembles LISP with less syntactic sugar. Internally a Combo program is represented as a program tree. • Composer: In the PLN design, a rule is denoted a composer if it needs premises for generating its conse

p the rules might profitably be ported into the Atomspace as ImplicationLinks. • Representation Building: A stage within MOSES, wherein a candidate Combo program tree (within a deme) is modified by replacing one or more tree nodes with alternative tree nodes, thus obtaining a new, different candidate

. • Imitation Learning: Learning via copying what some other agent is observed to do. • Implication: Often refers to an ImplicationLink between two PredicateNodes, indicating an (extensional, intensional or mixed) logical implication. • Implicit Knowledge Representation: Representation of knowledge via having

d up the rules might profitably be ported into the Atomspace as ImplicationLinks. Representation Building: A stage within MOSES, wherein a candidate Combo program tree (within a deme) is modified by replacing one or more tree nodes with alternative tree nodes, thus obtaining a new, different candidate p

her the latter are learned via MOSES or via some other means. The textual realization of Combo resembles LISP with less syntactic sugar. Internally a Combo program is represented as a program tree. e Composer: In the PLN design, a rule is denoted a composer if it needs premises for generating its conseq

er atoms. Grounded- PredicateNodes and GroundedSchemaNodes connect to explicitly represented procedures (sometimes in the Combo language); ungrounded PredicateNodes and SchemaNodes are abstract and, like ConceptNodes, purely characterized by their relationships. Node Probability: Many PLN inference rules rely on