Intelligence, Mind, Self-Modif, Define Core Concepts AI Goertzel 2002

01:51 PM, August 17, 2007

What is a PATTERN?

A process P is a pattern IN an entity X (where X could be a person, a picture, an idea) hwere P 

approx. produces X and is simpler than X. 

X captures some regularity in the makeup of X. 

The set of all patterns in X is what I call the structure of X. 

Intelligence is the ability to achieve complex goals in a complex environment

� All else equal, the greater the total complexity of the set of goals that the organism can achieve, the greater the system?s intelligence 

� All else equal, the greater the complexity of the set of environments in which these goals are achieved, the greater the system?s intelligence 

Complexity of achieving goal G in environment E) 

Probability of the system achieving goal G in environment E 

for the various possible goals G and environments E. 

Goertzel (1994), in a similar spirit, portrays mind as a web of patterns ? a dynamic web, continually rebuilding itself by a dynamic in which each component, each pattern, continually modifies the other patterns that it?s related to. (Bob note: the patterns are models of REALITY as it has been filtered by MY CNS neurons). 

4. SOLOMONOFF INDUCTION - a simple but very inefficient AI SYSTEM.

 Worked out by Ray Solomonoff in 1978. 

Suppose you have a system with: some goals, receptors and actuators allowing it to perceive and act in an environment, a large amount of memory and processing power, and flexibility to rewrite most of its memory however it likes. The goals and the environment can be made as complex as one likes. Then the system can achieve arbitrarily great intelligence, defined in terms of satisfying its goals in its environment, as follows. 

Suppose that the system?s memory is divided into two parts: the metaprogram, and the current program . Since we are positing extremely ample computational resources, there is no problem allowing the current program and the metaprogram to operate simultaneously at all times.

The metaprogram works as follows . It creates and maintains a huge table which records, for each time t in the system?s history:

all percepts the system has observed up to time t

all actions the system has taken up to time t

the degree to which the system has satisfied its goals at time t

At each point in time, it searches the space of all programs of size less than N (where N is very, very large), and for each program it assesses two qualities: 

The size of the program

The utility of the program, i.e. the estimated degree to which the system would have achieved its goals if P had been its ?current program? during its entire past history

The metaprogram then chooses a program that maximizes a combination of size and utility.

In other words, it asks itself: ?What is a simple program P so that, if I had obeyed P in the past, I would have had a high probability of achieving my goals??

The most desirable program P is then selected as the current program, and allowed to govern the system for the immediate future ? until the metaprogram finds something better.

Obviously, the metaprogram is acting here as a general pattern recognition engine. In finding the optimal program P, it is searching for patterns in the past history of the system, patterns of historical perceptions and current actions that have led to goal-achievement.

(So, Bob: look at a common-place version of the metaprogram: I'll DO whatever worked in the past and beyond that - I'll modify my PROGRAM to incorporate that (until 

something better comes along). 

5. Varieties of Self-Modification

 This is gobbledy gook that translates to this ... 

Intelligent NOETIC self-modification means changing the systems KB and thereby making it smarter (by having changed its STATE). 

Intelligent DYNAMICAL self-mod. means changing is PROCESSING SPEED or dynamics thereby changing its intellgience. 

(add DRAM, up-grade processor). 

5.1 Substructural Self-Modification

While developing the concepts of noetic and dynamical self-modification, an attempt was made to define a related concept of substructural self-modification . This was intended to measure the degree by which the system modifies its own ?basic components.?

The intuitive concept is relatively simple. For instance, if a human learns new thought processes, this modifies his brain?s dynamics to a certain extent. On the other hand, if a human augments his brain with a neurochip that enables him to do arithmetic and algebra at high speeds, this modifies his knowledge base and dynamics to a very large extent. 

One would like to say that the neurochip expands the dynamical repertoire of the system in some fundamental sense. Once the chip is there, the system can do a lot of things it could not have done otherwise: for instance, compute 1757775555*466464444 in a tenth of a second. 

On the other hand, it is not clear to us at this point how this is really qualitatively different from dynamical self-modification. After all, learning a new cognitive skill allows one to carry out activities that could not have been carried out otherwise. 

The difference seems to be mainly one of extent. A neurochip suddenly allows a huge amount of new ?implicit dynamics.? It thus allows the formation of all sorts of system states that would have been impossible otherwise. 

In the physical world, without modifying its basic components, there is going to be a ceiling to the intelligence that any finite system can assume. ?Substructural self-modification? in the intuitive sense is thus necessary for dynamical and noetic self-modification to continue beyond a certain point. 

To formalize the notion of substructural self-modification, it seems to be necessary to take a slightly different point of view. For instance, one can consider a physical system in terms of an hierarchy of abstract state machines M1, M2,?,Mk, where each state of Mi is defined as a set of states of Mi-1, and the transitions between states of Mi are consistent with the transitions permitted between states of Mi-1. In the case of a computer program we may have, roughly speaking, 

M1 = computer hardware 

M2 = operating system 

M3 = programming language 

M4 = AI program 

M5 = Easily mutable parts of AI program 

Generally speaking, intelligent modifications to lower levels of the hierarchy will tend to cause higher degrees of noetic and dynamical self-modification. ?Substructural? self-modification as in the neurochip example occurs at a lower level than modification of learning algorithms via experiential adaptation. In Novamente, modifications to the underlying source code occur at a lower level than modifications to schema operating with a fixed-source-code system. 

Intelligence, Mind, Self-Modif, Define Core Concepts AI Goertzel 2002

Attachments