Philip D. Laird

Learn More
The basic question addressed in this paper is: how can a learning algorithm cope with incorrect training examples? Specifically, how can algorithms that produce an “approximately correct” identification with “high probability” for reliable data be adapted to handle noisy data? We show that when the teacher may make independent random errors in classifying(More)
Learning from experience to predict sequences of discrete symbols is a fundamental problem in machine learning with many applications. We present a simple and practical algorithm (TDAG) for discrete sequence prediction. Based on a text-compression method, the TDAG algorithm limits the growth of storage by retaining the most likely prediction contexts and(More)
We show that the familiar explanation-based generalization (EBG) procedure is applicable to a large family of programming languages, including three families of importance to AI: logic programming (such as Prolog); lambda calculus (such as LISP); and combinator languages (such as FP). The main application of this result is to extend the algorithm to domains(More)
The efficiency of learning from unclassified data (unsupervised learning) is examined by constructing a framework similar in style to the recent work on supervised concept learning inspired by Valiant. We define the framework and illustrate it with results on three model classes. The framework is compared to both the supervised learnability model and other(More)