Page 273 - DCAP310_INTRODUCTION_TO_ARTIFICIAL_INTELLIGENCE_AND_EXPERT_SYSTEMS

Unit 14: Types of Learning

more likely to transfer the common strategy into a subsequent negotiation task than were Notes
students who analyzed the same two cases separately.

14.8.3 Retrieval of Analogy: The Inert Knowledge Problem

Inert knowledge is information which one can express but not use. The process of understanding
by learners does not happen to that extent where the knowledge can be used for effective
problem-solving in realistic situations. The phenomenon of inert knowledge was first described
in 1929 by Alfred North Whitehead:
“Theoretical ideas should always find important applications within the pupil’s curriculum. This is not an
easy doctrine to apply, but a very hard one. It contains within itself the problem of keeping knowledge alive,
of preventing it from becoming inert, which is the central problem of all education.”
An example for inert knowledge is vocabulary of a foreign knowledge which is available
during an exam but not in a real situation of communication.
An explanation for the problem of inert knowledge is that people often encode knowledge to a
specific situation, so that later remindings occur only for highly similar situations

In contrast so called conditionalized knowledge is knowledge about something which includes
also knowledge as to the contexts in which that certain knowledge will be useful.

Self Assessment

State whether the following statements are true or false:

15. Analogy plays an important role in learning and instruction.
16. Learning from cases is often difficult than learning principles directly.

14.9 Explanation-based Learning (EBL)

Explanation-based learning (EBL) is a form of machine learning that exploits a very strong, or
even perfect, domain theory to make generalizations or form concepts from training examples.
An example of EBL using a perfect domain theory is a program that learns to play chess by being
shown examples. A specific chess position that contains an important feature, say, “Forced loss
of black queen in two moves,” includes many irrelevant features, such as the specific scattering
of pawns on the board. EBL can take a single training example and determine what are the
relevant features in order to form a generalization. A domain theory is perfect or complete if it
contains, in principle, all information needed to decide any question about the domain. For
example, the domain theory for chess is simply the rules of chess. Knowing the rules, in principle
it is possible to deduce the best move in any situation. However, actually making such a deduction
is impossible in practice due to combinatoric explosion. EBL uses training examples to make
searching for deductive consequences of a domain theory efficient in practice. An EBL system
works, by finding a way to deduce each training example, from the system’s existing database of
domain theory. Having a short proof of the training example extends the domain-theory database,
enabling the EBL system to find and classify future examples that are similar to the training
example very quickly. The main drawback of the method, the cost of applying the learned proof
macros as these become numerous.

Did u know? Humans appear to learn quite a lot from one example.

LOVELY PROFESSIONAL UNIVERSITY 267