Embed
Email

prism

Document Sample

Shared by: gegeshandong
Categories
Tags
Stats
views:
1
posted:
10/27/2011
language:
English
pages:
9
PRISM: A Probabilistic

Language for Modeling and

Learning

Joint work with Taisuke Sato (Tokyo

Institute of Technology)







by Neng-Fa Zhou 1

What is PRISM?

 PRISM = Probabilistic Prolog

direction(D):-

msw(coin,Face),

(Face==head->D=left;D=right).



 Three execution modes

– Sample execution

– Probability calculation

– Learning

by Neng-Fa Zhou 2

Features

 Use logic programs to describe probabilistic

choices and their consequences

 Probability distributions (parameters of switches)

can be learned automatically from samples

 Tabling is used in probabilistic computations and

learning (resembles dynamic programming)

 A high level yet efficient modeling language

(Subsumes HMM, PCFG, and discrete Bayesian

networks)



by Neng-Fa Zhou 3

Applications

 Probabilistic modeling and learning for

problem domains where randomness or

uncertainty is involved

– Stochastic language processing

– Gene sequence analysis

– Game analysis

– Optimization (e.g., performance tuning)



by Neng-Fa Zhou 4

PRISM : the Language

 Probability distributions and switches

values(coin,[head:0.5,tail:0.5]).

direction(D):-

msw(coin,Face),

(Face==head->D=left;D=right).



 Sample execution: sample(Goal)

 Probability calculation: prob(Goal,P)

 Learning: learn(Facts)

by Neng-Fa Zhou 5

Assumptions

 Distribution assumption

• Let values(I,[o1:p1,…,on:pn]) be a sample space

declaration. pi = 1

• msw(I,V) always succeeds if V is a variable.



 Independence assumption

prob(AB) = prob(A)*prob(B)



 Exclusiveness assumption

prob(AB) = prob(A)+prob(B)



by Neng-Fa Zhou 6

Learning

Given a set of observed facts F, determine the probability

distributions for the switches to maximize the likelihood of F.









by Neng-Fa Zhou 7

Using Tabling (Dynamic

Programming) in Learning



hmm(L) :- hmm([a,b,a])

msw(init,Si),

hmm(Si,L). hmm(s0,[a,b,a]) hmm(s1,[a,b,a])



hmm(S,[]).

hmm(S,[C|L]) :- hmm(s0,[b,a]) hmm(s1,[b,a])

msw(out(S),C),

msw(tr(S),NextS), hmm(s0,[a]) hmm(s1,[a])

hmm(NextS,L).



values(init,[s0,s1]). hmm(s0,[]) hmm(s1,[])

values(out(_),[a,b]).

values(tr(_),[s0,s1]).

by Neng-Fa Zhou 8

Papers

1. T. Sato: A Statistical Learning Method for Logic

Programs with Distribution Semantics,

ICLP-95.

2. T. Sato and Y. Kameya: Parameter Learning

of Logic Programs for Symbolic-statistical Modeling,

Journal of Artificial Intelligence Research, 2001.

3. N.F. Zhou, T. Sato, K. Hasida: Toward a High-

performance System for Symbolic and Statistical

Modeling, Proc. IJCAI Workshop on Learning

Statistical Models from Relational Data, pp. 153-159,

2003.



by Neng-Fa Zhou 9



Related docs
Other docs by gegeshandong
Mar - Mr Hanson
Views: 0  |  Downloads: 0
WhatDoYouMeanHighest.Price
Views: 0  |  Downloads: 0
core data
Views: 0  |  Downloads: 0
jan-18-2009b
Views: 0  |  Downloads: 0
Status - California State University
Views: 0  |  Downloads: 0
PHASE ONE
Views: 0  |  Downloads: 0
By registering with docstoc.com you agree to our
privacy policy

You are almost ready to download!

You are almost ready to download!