[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

VMs: Four column model/paradigm...

Hi Dennis,

At 21:27 14/11/2003 -0600, Dennis wrote:
FWIW.  I like these two paradigms for their simplicity.
Firth said his paradigm accounted for ~250 Voynichese
words out of a possible ~420 it could generate.

Does anyone see any further conclusions? I'm thinking.

I've developed my "four column" model (from f78r) into something more substantial: here's a diagram of a Markov model which explains what I'm thinking...


Each box represents a Markov state, starting with [Start] and ending with [End].

The two red boxes refer to hidden Markov states (which I've guessed at) - these keep the complexity of the diagram down, and (if I've guessed them right) may also be suggestive of a deeper understanding of the VMs' word-structure.

Each arrow represents a transition from one Markov state to the next - these travel across columns (ie, from left to right), with the exception of the two dotted lines in the middle (between [e/ee] and [ckh|cth]), which ATM mean "only ever follow a maximum of one of these within any given word". There may be better ways of representing this, but what the hey. :-)

I haven't yet worked out how many VMs-like words this model should generate - with all the possible permutations of paths, it's not the kind of thing you'd want to be calculating in our head. :-o Any suggestions?

Cheers, .....Nick Pelling.....

______________________________________________________________________ To unsubscribe, send mail to majordomo@xxxxxxxxxxx with a body saying: unsubscribe vms-list