Page 165 - DCAP506_ARTIFICIAL_INTELLIGENCE

Unit 12: Learning

Learning includes a broad range of phenomenon: Notes
 Skill refinement: Practice makes abilities perk up. More you play, better you obtain
 Knowledge acquisition: Knowledge is usually attained via experience

12.1 Meaning of Learning

Learning is distinguished into a number of different forms. The simplest is learning by trial-
and-error. For example, a simple program for solving mate-in-one chess problems might try
out moves at random until one is found that achieves mate. The program remembers the
successful move and next time the computer is given the same problem it is able to produce the
answer immediately. The simple memorizing of individual items – solutions to problems,
words of vocabulary, etc. – is known as rote learning.
Rote learning is relatively easy to implement on a computer. More challenging is the problem
of implementing what is called generalization. Learning that involves generalization leaves the
learner able to perform better in situations not previously encountered. A program that learns
past tenses of regular English verbs by rote will not be able to produce the past tense of e.g.
“jump” until presented at least once with “jumped”, whereas a program that is able to generalize
from examples can learn the “add-ed” rule, and so form the past tense of “jump” in the absence
of any previous encounter with this verb. Sophisticated modern techniques enable programs to
generalize complex rules from data.

Self Assessment

Fill in the blanks:
1. ......................... is defined as modifications in the system that are adaptive in the sense that
they facilitate the system to do the similar task or tasks taken from the similar population
more competently and more successfully the next time.
2. Learning that involves ......................... leaves the learner able to perform better in situations
not previously encountered.

12.2 Rote Learning

Rote learning is the fundamental learning activity. It is also known as memorization since the
knowledge, without any alteration is, just copied into the knowledge base. As calculated values
are accumulated, this technique can save a important amount of time.
Rote learning method can also be utilized in multifaceted learning systems provided sophisticated
techniques are engaged to use the accumulated values faster and there is a simplification to keep
the number of amassed information down to a handy level.

Example: Checkers-playing program accesses this technique to study the board positions
it assesses in its look-ahead hunt.

Example: A simple example of rote learning is caching
 Amass computed values (or large piece of data)
 Recall this information when needed by computation.

LOVELY PROFESSIONAL UNIVERSITY 159