.
FRDCSA | internal codebases | Learner

Learner Architecture Diagram: GIF

Jump to: Project Description | Capabilities

Project Description

Capabilities

• antispam-console - The rule learner for the system has to learn rules that have a lot of data to substantiate their effectiveness, for instance 50/50. It should also allow me to write additional production rules in Perl, for instance, has met 5 or more rules... etc.
• Maybe use Snow as part of perllib learner.
• Can feed learner::Method some SGML annotated text and expect it to learn the annotation scheme. It can do this by applying all the learners. It may wish to check with the author. That has to be determined before mission critical usage.
• Figure out what is wrong with autoclassification. Add more features. Get more input. Perhaps use Weka with the output to generate some kind of learner.
• We should develop a system for developing systems. In other words, boss should have high-level design criteria in mind. In other words, let us have a better defined approach to building systems. To build the TDT, we should (after first searching for other systems) collect data, choose a learner, implement the learner, etc.
• I'm a good learner.
• code-monkey ought to have an adaptive learner, that determines how to do various packaging requirements. Should use SPARK or some such thing.
• Hook up learner and quac to create a question question-asker/question-answerer feedback loop
• Using a text similarity system, we can first automatically annotate texts where projects get their descriptions. Then, we can train a learner on this information to get automatic extractions of documentation.
• obviously the learner to radar must take into account the arguments as well as the search term for learning
• Necessary to make estimations of project life in order to determine whether to use the software. Set up featured learners to predict this. Call this the learner.