This paper describes a program that learns procedures by examining worked-out examples in a textbook and bv working problems two kinds of production (If-then) rules are created: working forward rules that produce an action when a proceduie is executed and difference rules that suggest operators from observed transformations. Dining example learning, the program examines two states in an example, fig tires out the operator that produced the second state and creates a production with some part ot the first line in the condition with the operator-tor in the action. During learning by working problems, the program generates its own example trace by problem solving and uses the same example learning techniques.
[1]
Donald A. Waterman,et al.
Adaptive Production Systems
,
1975,
IJCAI.
[2]
K VanLehn.
Felicity Conditions for Human Skill Acquisition: Validating an AI (Artificial Intelligence)-Based Theory.
,
1983
.
[3]
Thomas G. Dietterich.
Learning About Systems That Contain State Variables
,
1984,
AAAI.
[4]
Kurt Van Lehn,et al.
Felicity conditions for human skill acquisition: validating an al-based theory
,
1983
.
[5]
Allen Newell,et al.
Human Problem Solving.
,
1973
.
[6]
John R. Anderson,et al.
Complex Learning Processes
,
1978
.