Sciweavers

Share
ATAL
2009
Springer

MABLE: a framework for learning from natural instruction

10 years 2 months ago
MABLE: a framework for learning from natural instruction
The Modular Architecture for Bootstrapped Learning Experiments (MABLE) is a system that is being developed to allow humans to teach computers in the most natural manner possible: by using combinations of descriptions, demonstrations, and feedback. MABLE is a highly modular, well-engineered, and extendable system that provides generalized services, such as control, knowledge representation, and execution management. MABLE works by accepting instruction from a teacher and forms concrete learning tasks that are fed to state-of-the-art machine learning algorithms. To make the learning tractable, specialized heuristics, in the form of learning strategies, are used to derive bias from the instruction. The output of the learning is then incorporated into the system’s background knowledge to be used in performing tasks or as the basis for simplifying the process of learning difficult concepts. Although still in development, MABLE has already demonstrated the ability to learn four different...
Roger Mailler, Daniel Bryce, Jiaying Shen, Ciaran
Added 26 May 2010
Updated 26 May 2010
Type Conference
Year 2009
Where ATAL
Authors Roger Mailler, Daniel Bryce, Jiaying Shen, Ciaran O'Reilly
Comments (0)
books