Coder Social home page Coder Social logo

Comments (7)

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024

Original comment by [email protected] on 23 Oct 2009 at 3:14

from aima-java.

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024

Original comment by [email protected] on 13 Nov 2009 at 1:12

  • Added labels: Milestone-core-1.0.0
  • Removed labels: Milestone-Release1.0

from aima-java.

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024
[deleted comment]

from aima-java.

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024
Ciaran,

Working on CURRENT-BEST-LEARNING. Have some stuff laid out(see 
https://github.com/andrewsbrown/aima-java/blob/master/aima-core/src/main/java/ai
ma/core/learning/learners/CurrentBestLearner.java) but would appreciate any 
advice, especially regarding how to specialize() and generalize() the 
hypotheses using the FOL packages. Not super clear on those.

Andrew 

Original comment by [email protected] on 9 Apr 2012 at 7:21

from aima-java.

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024
Hi Andrew,

Basic specialization and generalization can be achieved by using conjuncts and 
disjuncts respectively (a more general solution is likely required to work 
properly, i.e. you'll have to search through the space of generalizations and 
specializations from a particular hypothesis/formula). However, this is only 
part of the issues you'll run into here. I played with this a couple of years 
ago and basically the theorem provers implemented are too slow in order to be 
able test the hypothesis generated for whether they are correct for an example 
or not (in particular I was using the example 19.1 from pg 769 - to run current 
best learning you have to perform this type of test a large number of times). 
Without a more efficient theorem prover or an acceptance of simpler hypothesis 
spaces to be searched, it will be difficult to get this and related algorithms 
in Chapter 19 functioning properly. 

Original comment by [email protected] on 9 Apr 2012 at 9:11

from aima-java.

GoogleCodeExporter avatar GoogleCodeExporter commented on May 23, 2024
Ciaran,

What you are saying makes sense. The hypothesis space will be huge, especially 
because I was going to combine all possible attributes into hypotheses of 1 to 
k attributes. I will look into other stuff and come back to this if I have some 
brilliant idea.

Andrew

Original comment by [email protected] on 9 Apr 2012 at 10:19

from aima-java.

samagra14 avatar samagra14 commented on May 23, 2024

This was resolved in #414.

from aima-java.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.