Tuesday, February 19, 2008

Change problem context, moving it (the problem) in a more comfortable one (context)

The challenge is to try to imagine the software problem of information units composition/chaining as "chemical bonds", as links between composable info units. May or may not be a way to find a solution, but it is a so strange and interesting analysis approach, why not to try ? Can a person extract a problem from its original context, forget this context and translate it in another different context, to have a different and more familiar (for our brains) point of view ?


Vincenzo said...

As I wrote before, let's consider a genetic approach:
In common genetic algorithm one considers the snapshot of the system (or allele) and applies genetic techniques to give birth to new generations. These generations are then filtered using a fitness function.

In our system we don't know the fitness function so we can view the approach the other way around:
the genes are the chains (how those chains are formed is still to be defined). Analyzing the history of the system we can define a measure of the quality of it and derive the fitness function from the evolution of the different generations.
Are we able then to define the inference rules starting from the analysis of the evolution of the system ?
The point here is to apply random (or quasi-random) population of chains generation to derive inference rules for the expert system.

Vincenzo said...

To sum up things:

Chain = Gene
Allele = Snapshot of the system

Fitness Function = ???