Learning and Reasoning With Constraints
Abstract
This is the most distinguishing chapter of the book, where the environmental interactions are modeled by different constraints that are classified according to their mathematical structure. Constraint machines are introduced, which carry out learning and inference according to the unified principle of parsimonious constraint satisfaction. Like for kernel machines, depending on the given constraints, this leads us to establish natural representational results on the structure of those machines. An insight is given for setting the process of learning and inference in the framework of life-long learning, along with advanced issues on the automatic extraction of constraints. The chapter ...
Get Machine Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
