Pack Ann: Pepl - 2.0.2

Pepl is now available on the packs server.

Installation via the usual

	?-  pack_install( pepl ).


Pepl is an implementation of the FAM algorithm [1].
Given some data, Pepl can estimate/fit the probabilistic labels of a Stochastic Logic Program.
Failure adjusted maximisation (FAM) is an EM algorithm for SLPs. 

For example, for SLP source file jc_ml_S1.slp (see [1]) 

0.5:: s(X,p) :- p(X), p(X).
0.5:: s(X,q) :- q(X).
0.5:: p(a).
0.5:: p(b).
0.5:: q(a).
0.5:: q(b).

and data file jc_ml_S1_data.pl

frequencies([s(a,p)-4,s(a,q)-3,s(b,p)-2,s(b,q)-3]).

the call

   fam( [goal(s(_A,_B)),slp(jc_ml_S1),datafile('jc_ml_S1_data.pl'),final_pps(PPs)] ).

succeeds with

   PPs = [0.6602,0.3398,0.5858,0.4142,0.5,0.5]


Pepl's home page: http://stoics.org.uk/~nicos/sware/pepl


Regards,

Nicos Angelopoulos
---
http://stoics.org.uk/~nicos/

[1]  James Cussens, Parameter estimation in stochastic logic programs. Machine Learning, 44(3):245-271, 2001