Presented By

Ms. Neha V. Mogre, Asst.Prof. CSE

Subject Teacher
UNIT I: Introduction: What is AI? History & Applications,
Artificial intelligence as representation & Search, Production
system, Basics of problem solving: problem representation
paradigms, defining problem as a state space representation,
Characteristics.

UNIT II: Search Techniques: Uninformed Search techniques,

Informed Heuristic Based Search, Generate and test, Hill-climbing,
Best-First Search, Problem Reduction, and Constraint Satisfaction.

UNIT III: Knowledge representation: Knowledge representation

Issues: First order logic, Predicate Logic, Structured Knowledge
Representation: Backward Chaining, Backward Chaining,
Resolution ,Semantic Nets, Frames, and Scripts, Ontology.
UNIT IV: Uncertainty: Handing uncertain knowledge, rational
decisions, basics of probability, axioms of probability, Baye’s Rule
and conditional independence, Bayesian networks, Exact and
Approximate inference in Bayesian Networks, Fuzzy Logic.

UNIT V: Learning: What is learning?, Knowledge and learning,

Learning in Problem Solving, Learning from example, learning
probabilistic models, Formal Learning Theory

UNIT VI: Expert Systems: Fundamental blocks, Knowledge

Engineering, Knowledge Acquisition, Knowledge Based Systems,
Automated Reasoning, Understanding Natural language
Textbooks:
1. E. Rich and K. Knight, Artificial Intelligence, Tata McGraw
Hill, 2008.
2.Artificial intelligence and soft computing for beginners  by
Anandita Das Bhattachargee, Shroff Publishers
3.Artificial Intelligence – A Practical Approach : Patterson , Tata
McGraw Hill, 3rd Edition

Reference Books:
1.Introduction to Artificial Intelligence – Charniak (Pearson
Education)
BECSE306T AI Course Outcome

Ability to Understand AI and corresponding problems related

CO1
with AI.
CO2 Ability to understand various search techniques.

CO3 Ability to understand the concepts of knowledge representation.

Understand the theory of uncertainty and appreciate how

CO4 uncertainty is being tackled in the knowledge representation and
reasoning process based on fuzzy set.
CO5 Ability to understand the concepts of expert system.

Ability to aware the challenges in Natural Language

CO6
understanding.
 UNIT 5

Learning
• Learning is one of the fundamental building blocks of artificial
intelligence (AI) solutions.
•   From a conceptual standpoint, learning is a process that improves
the knowledge of an AI program by making observations about its
environment.
• From a technical/mathematical standpoint, AI learning processes
focused on processing a collection of input-output pairs for a
specific function and predicts the outputs for new inputs.
• According to Herbert Simon, learning denotes changes in a system
that enable a system to do the same task more efficiently the next
time.
• Arthur Samuel stated that, "Machine learning is the subfield of
computer science, that gives computers the ability to learn
without being explicitly programmed ".
• In 1997, Mitchell proposed that, " A computer program is said to
learn from experience 'E' with respect to some class of
tasks 'T' and performance measure 'P', if its performance at tasks
in 'T', as measured by 'P', improves with experience E ".
• The main purpose of machine learning is to study and design the
algorithms that can be used to produce the predicates from the
given dataset.
• Besides these, the machine learning includes the agents
percepts  for acting as well as to improve their future
performance.
The following tasks must be learned by an agent.
• To predict or decide the result state for an action.
• To know the values for each state(understand which state has high
or low vale).
• To keep record of relevant percepts.
Why do we require machine learning?
• Machine learning plays an important role in improving and
understanding the efficiency of human learning.
• Machine learning is used to discover a new things not known to
many human beings.
The following tasks must be learned by an agent.
• To predict or decide the result state for an action.
• To know the values for each state(understand which state has high
or low vale).
• To keep record of relevant percepts.
Why do we require machine learning?
• Machine learning plays an important role in improving and
understanding the efficiency of human learning.
• Machine learning is used to discover a new things not known to
many human beings.
 Stimuli
examples Feedback

Environ-
ment Knowledge Critic
Representation Performance
Or Evaluator

Teacher

Response

Performance
Component
Tasks

Fig. General Learning Model

• Learning can be broadly classified into three categories, as
mentioned below, based on the nature of the learning data and
interaction between the learner and the environment.
1. Supervised Learning
2. Unsupervised Learning
3. Semi-supervised Learning
• Supervised learning is commonly used in real world applications, such as
face and speech recognition, products or movie recommendations, and
sales forecasting. Supervised learning can be further classified into two
types - Regression and Classification.
• Regression trains on and predicts a continuous-valued response, for
example predicting real estate prices.
• Classification attempts to find the appropriate class label, such as
analyzing positive/negative sentiment, male and female persons, benign
and malignant tumors, secure and unsecure loans etc.
• In supervised learning, learning data comes with description, labels,
targets or desired outputs and the objective is to find a general rule that
maps inputs to outputs. This kind of learning data is called labeled data.
The learned rule is then used to label new data with unknown outputs.
• Supervised learning is commonly used in real world applications, such as
face and speech recognition, products or movie recommendations, and
sales forecasting. Supervised learning can be further classified into two
types - Regression and Classification.
• Regression trains on and predicts a continuous-valued response, for
example predicting real estate prices.
• Classification attempts to find the appropriate class label, such as
analyzing positive/negative sentiment, male and female persons, benign
and malignant tumors, secure and unsecure loans etc.
• In supervised learning, learning data comes with description, labels,
targets or desired outputs and the objective is to find a general rule that
maps inputs to outputs. This kind of learning data is called labeled data.
The learned rule is then used to label new data with unknown outputs.
• Supervised learning deals with learning a function from available
training data. Here, a learning algorithm analyzes the training data
and produces a derived function that can be used for mapping new
examples.
• There are many supervised learning algorithms such as
– Logistic Regression
– Neural networks
– Support Vector Machines (SVMs)
– Naive Bayes classifiers.
• Common examples of supervised learning include classifying e-
mails into spam and not-spam categories, labeling webpages based
on their content, and voice recognition.
• Unsupervised learning is used to detect anomalies, outliers, such as
fraud or defective equipment, or to group customers with similar
behaviors for a sales campaign.
• It is the opposite of supervised learning. There is no labeled data
here.
• When learning data contains only some indications without any
description or labels, it is up to the coder or to the algorithm to find
the structure of the underlying data, to discover hidden patterns,
or to determine how to describe the data. This kind of learning
data is called unlabeled data.
• Unsupervised learning algorithms are extremely powerful tools for
analyzing data and for identifying patterns and trends.
• They are most commonly used for clustering similar input into
logical groups.
• Unsupervised learning algorithms include
– Kmeans
– Random Forests
– Hierarchical clustering and so on.
• If some learning samples are labeled, but some other are not
labeled, then it is semi-supervised learning.
• It makes use of a large amount of unlabeled data for training and a
small amount of labeled data for testing.
• Semi-supervised learning is applied in cases where it is expensive to
acquire a fully labeled dataset while more practical to label a small
subset.
• For example, it often requires skilled experts to label certain
remote sensing images, and lots of field experiments to locate oil at
a particular location, while acquiring unlabeled data is relatively
easy.
• Learning data gives feedback so that the system adjusts to dynamic
conditions in order to achieve a certain objective.
• The system evaluates its performance based on the feedback
responses and reacts accordingly.
• The best known instances include self-driving cars and chess
master algorithm AlphaGo.
 Types of Learning
• Rote Learning
• Learning by taking advice
• Learning by examples
• Learning by analogy
 Rote Learning
Rote Learning is basically memorisation techniques based on
repeation.
• Saving knowledge so it can be used again.
• Retrieval is the only problem.
• No repeated computation, inference or query is necessary.
 Rote Learning
A simple example of rote learning is caching
• Store computed values (or large piece of data)
• Recall this information when required by computation.
• Significant time savings can be achieved.
• Many AI programs (as well as more general ones) have used
caching very effectively.
• Memorisation is a key necessity for learning:
• It is a basic necessity for any intelligent program -- is it a
separate learning process?
• Memorisation can be a complex subject -- how best to store
knowledge?
• Rote learning is basically a simple process. However it does
illustrate some issues that are relevant to more complex
learning issues.
• It is a basic learning activity.
• It is also called memorization because the knowledge,
without the modification is simply copied into the knowledge
base.
• As computed values are stored this technique can save
significant amount of time.
• Rote learning can also be used in complex learning systems
provided sophisticated techniques are employed to use the
stored values faster and there is a generalization to keep the
number of stored information down to a manageable level.
• Checkers learning program uses this
technique to learn the board positions it
evaluates in its look-ahead search.
 Advantages
• Ability to rapidly review fundamental realities
• Helps create primary information
 Disadvantages
• Can be tedious.
• Easy to lose focus.
• Doesn’t take into consideration a more thoughtful
understanding of a subject.
• Doesn’t energize the utilization of social skills.
• No association between new and past learning may
bring about an inappropriate impression or
understanding an idea
 Learning by taking advice
• The idea of advice taking in AI based learning was proposed as
early as 1958 (McCarthy).
• However very few attempts were made in creating such systems
until the late 1970s. Expert systems providing a major impetus in
this area.
There are two basic approaches to advice taking:
• Take high level, abstract advice and convert it into rules that can
guide performance elements of the system. Automate all aspects
of advice taking
• Develop sophisticated tools such as knowledge base editors and
debugging.
• These are used to aid an expert to translate his expertise into
detailed rules. Here the expert is an integral part of the learning
system. Such tools are important in expert systems area of AI.
 Learning by taking advice
• The knowledge must be transformed into an operational form
before stored in the knowledge base.
• Moreover the reliability of the source of knowledge should be
considered.
• This is a simple form of learning.
• Suppose a programmer writes a set of instructions to instruct the
computer what to do, the programmer is a teacher and the
computer is a student. Once learned (i.e. programmed), the system
will be in a position to do new things.
• The advice may come from many sources: human experts, internet
to name a few.
• This type of learning requires more inference than rote learning.
• The knowledge must be transformed into an operational form
before stored in the knowledge base.
• Moreover the reliability of the source of knowledge should be
considered.
• The system should ensure that the new knowledge is conflicting
with the existing knowledge.
• FOO (First Operational Operationaliser), for example, is a learning
system which is used to learn the game of Hearts.
• It converts the advice which is in the form of principles, problems,
and methods into effective executable (LISP) procedures (or
knowledge).
• Now this knowledge is ready to use.
 Learning by analogy
• Analogical reasoning is a powerful mechanism for exploiting
past experience in planning and problem solving.
• An analogical transformation process is developed to extract
knowledge from past successful problem-solving situations
that bear a strong similarity to the current problem.
• When encountering a new problem situation, a person is
reminded of past situations that bear strong similarity to the
present problem 
 Case-Based Reasoning (CBR)
• One technique in learning by analogy is case-based reasoning
(CBR).  
• Case-based reasoning (CBR), broadly construed, is the process of
solving new problems based on the solutions of similar past
problems.
• In CBR, a case holds a problem statement and its solution.
• When a new problem is encountered, the system searches its case
base for the best case typically one that matches the new problem
most closely.  
• Then based on the differences between the new problem and the
best case’ problem statement, the system adapts the best case’
solution accordingly.
 Case-Based Reasoning (CBR)
• It is collection of cases
– It stores cases in Case Base
• CBR is based on Human Information Processing (HIP) model
in some problem areas
– Thinking about how human process information
– Try to remember previous case/recall similar cases & modify to fit a
new situation
• Ex: Law Diagnosis, strategic planning
• Human experts heavily depend on past experience when
solving new problems
 Learning by Examples
or Induction Learning
• Often times, we learn by classifying things into different labels
and then “inferring” the common characteristics of each label.  
• This type of learning is especially useful in classification tasks:
• the “learned” or “trained” system can classify a previously
unseen entity (or instance) into one of the group by comparing
the instance’s attribute values to the common characteristics of
the groups. 
• Induction learning is carried out on the basis of supervised
learning.
• In this learning process, a general rule is induced by the system
from a set of observed instance.
• From another perspective, this type of learning can be viewed
as learning the decision path to correctly label an instance. 
•  And that decision path can be represented as part of a
decision tree, where a node is a decision point, branches are
possible values of a decision, and leaves are classification
labels.
An intelligent agent may have to learn, for instance, the following
components:
• A direct mapping from conditions on the current state to actions
• A means to infer relevant properties of the world from the
percept sequence
• Information about the way the world evolves and about the
results of possible actions the agent can take
• Utility information indicating the desirably of world states
• Action-value information indicating the desirably of actions
• Goals that describe classes of states whose achievement
maximizes the agent’s utility
The type of feedback available for learning determines the nature of
the learning problem that the agent faces
• Supervised learning involves learning a function from examples of
its inputs and outputs
• Unsupervised learning involves learning patterns in the input
when no specific output values are supplied
• In reinforcement learning the agent must learn from
reinforcement (reward, punishment, less exact feedback than in
supervised learning)
• In semi-supervised learning we are given a few labeled examples
and must make what we can of a large collection of unlabeled
examples
 Learning by discovery
• Learning by discovery is sometimes considered as the highest
form of machine learning because it discovers new
knowledge or information. 

• To do that, a system will need to be able to generate

concepts, for example", and will also need to be able to
evaluate and identify these concepts are new and interesting.