Explanation-based Learning in Artificial Intelligence
Explanation-based Learning:
An EBL system attempts to learn from a single example x by explaining why x is an example of the target concept (predicate) instead of learning through a large number of examples. The explanation is then generalized and the system’s performance is improved through the availability of background knowledge. This process is known as memorisation.
It is defined as the phenomenon to accumulate a database of input/output pairs in which when a function is called, it first checks the database to see whether it can avoid solving the problem.
Explanation-Based Learning Algorithm:
Step-1: Given an example say of fork of differentiation), it constructs proof such that the goal predicate applies to the example using the available background knowledge.
Step-2: In parallel, construct a generalized proof tree for the variables goal using the same inference steps as in the original proof.
Step-3: Construct a new rule whose left side consists of the leaves of the proof tree and whose right-hand side is the variable goal.
Step-4: Drop any conditions which are true regardless of the values of the variables in the goal.