Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)
We address the problem of learning an unknown function by pu tting together several pieces of information (hints) that we know about the function. We introduce a method that generalizes learn(cid:173) ing from examples to learning from hints. A canonical representa(cid:173) tion of hints is defined and illustrated for new types of hints. All the hints are represented to the learning process by examples, and examples of the function are treated on equal footing with the rest of the hints. During learning, examples from different hints are selected for processing according to a given schedule. We present two types of schedules; fixed schedules that specify the relative em(cid:173) phasis of each hint, and adaptive schedules that are based on how well each hint has been learned so far. Our learning method is compatible with any descent technique that we may choose to use.