Module 13
Natural Language Processing
Version 1 CSE IIT, Kharagpur
Lesson 41
Parsing
Version 1 CSE IIT, Kharagpur
13.3 Natural Language Generation
The steps in natural language generation are as follows.
Meaning representation Utterance Planning Meaning r
Module 13
Natural Language Processing
Version 1 CSE IIT, Kharagpur
13.1 Instructional Objective
The students should understand the necessity of natural language processing in building an intelligent system Students should understand the difference betwee
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 39
Neural Networks - III
Version 1 CSE IIT, Kharagpur
12.4.4 Multi-Layer Perceptrons
In contrast to perceptrons, multilayer networks can learn not only multiple decision boundaries, but the bo
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 38
Neural Networks - II
Version 1 CSE IIT, Kharagpur
12.4.3 Perceptron
Definition: Its a step function based on a linear combination of real-valued inputs. If the combination is above a thresh
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 37
Learning and Neural Networks - I
Version 1 CSE IIT, Kharagpur
12.4 Neural Networks
Artificial neural networks are among the most powerful learning models. They have the versatility to appro
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 36
Rule Induction and Decision Tree - II
Version 1 CSE IIT, Kharagpur
Splitting Functions
What attribute is the best to split the data? Let us remember some definitions from information theory
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 35
Rule Induction and Decision Tree - I
Version 1 CSE IIT, Kharagpur
12.3 Decision Trees
Decision trees are a class of learning models that are more robust to noise as well as more powerful as
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
Lesson 34
Learning From Observations
Version 1 CSE IIT, Kharagpur
12.2 Concept Learning
Definition: The problem is to learn a function mapping examples into two classes: positive and negative. We are
Module 12
Machine Learning
Version 1 CSE IIT, Kharagpur
12.1 Instructional Objective
The students should understand the concept of learning systems Students should learn about different aspects of a learning system Students should learn about taxonomy of
Module 11
Reasoning with uncertainty-Fuzzy Reasoning
Version 1 CSE IIT, Kharagpur
Lesson 32
Fuzzy Reasoning Continued
Version 1 CSE IIT, Kharagpur
11.4 Fuzzy Inferencing
The process of fuzzy reasoning is incorporated into what is called a Fuzzy Inferencin
Module 11
Reasoning with uncertainty-Fuzzy Reasoning
Version 1 CSE IIT, Kharagpur
Lesson 31
Fuzzy Set Representation
Version 1 CSE IIT, Kharagpur
11.3 Fuzzy Sets: BASIC CONCEPTS
The notion central to fuzzy systems is that truth values (in fuzzy logic) or
Module 11
Reasoning with uncertainty-Fuzzy Reasoning
Version 1 CSE IIT, Kharagpur
11.1 Instructional Objective
The students should understand the use of fuzzy logic as a method of handling uncertainty The student should learn the definition of fuzzy sets
Module 10
Reasoning with Uncertainty Probabilistic reasoning
Version 1 CSE IIT, Kharagpur
Lesson 29
A Basic Idea of Inferencing with Bayes Networks
Version 1 CSE IIT, Kharagpur
10.5.5 Inferencing in Bayesian Networks
10.5.5.1 Exact Inference The basic inf
Module 10
Reasoning with Uncertainty Probabilistic reasoning
Version 1 CSE IIT, Kharagpur
Lesson 27
Probabilistic Inference
Version 1 CSE IIT, Kharagpur
10.4 Probabilistic Inference Rules
Two rules in probability theory are important for inferencing, name
Module 10
Reasoning with Uncertainty Probabilistic reasoning
Version 1 CSE IIT, Kharagpur
10.1 Instructional Objective
The students should understand the role of uncertainty in knowledge representation Students should learn the use of probability theory
Module 9
Planning
Version 1 CSE IIT, Kharagpur
Lesson 25
Planning algorithm - II
Version 1 CSE IIT, Kharagpur
9.4.5 Partial-Order Planning
Total-Order vs. Partial-Order Planners Any planner that maintains a partial solution as a totally ordered list of st
Module 9
Planning
Version 1 CSE IIT, Kharagpur
Lesson 24
Planning algorithm - I
Version 1 CSE IIT, Kharagpur
9.4 Planning as Search
Planning as Search: There are two main approaches to solving planning problems, depending on the kind of search space that
Module 9
Planning
Version 1 CSE IIT, Kharagpur
Lesson 23
Planning systems
Version 1 CSE IIT, Kharagpur
9.3 Planning Systems
Classical Planners use the STRIPS (Stanford Research Institute Problem Solver) language to describe states and operators. It is an
Module 9
Planning
Version 1 CSE IIT, Kharagpur
9.1 Instructional Objective
The students should understand the formulation of planning problems The student should understand the difference between problem solving and planning and the need for knowledge re
Module 8
Other representation formalisms
Version 1 CSE IIT, Kharagpur
Lesson 21
Frames II
Version 1 CSE IIT, Kharagpur
Slots as Objects
How can we to represent the following properties in frames?
Attributes such as weight, age be attached and make sense
Module 8
Other representation formalisms
Version 1 CSE IIT, Kharagpur
Lesson 20
Frames - I
Version 1 CSE IIT, Kharagpur
8.4 Frames
Frames are descriptions of conceptual individuals. Frames can exist for `real' objects such as `The Watergate Hotel', sets o
Module
8
Other representation
formalisms
Version 1 CSE IIT, Kharagpur
8.1 Instructional Objective
The students should understand the syntax and semantic of semantic networks
Students should learn about different constructs and relations supported by seman
Module 7
Knowledge Representation and Logic (Rule based Systems)
Version 1 CSE IIT, Kharagpur
Lesson 18
Rule based Systems - II
Version 1 CSE IIT, Kharagpur
7.2.5 Programs in PROLOG
These minimal notes on Prolog show only some of its flavor. Here are fact
Module 7
Knowledge Representation and Logic (Rule based Systems)
Version 1 CSE IIT, Kharagpur
7.1 Instructional Objective
The students should understand the use of rules as a restricted class of first order logic statements The student should be familiar
Module 6
Knowledge Representation and Logic (First Order Logic)
Version 1 CSE IIT, Kharagpur
Lesson 16
Inference in FOL - II
Version 1 CSE IIT, Kharagpur
6.2.9 Proof as Search
Up to now we have exhibited proofs as if they were found miraculously. We gave
Module 6
Knowledge Representation and Logic (First Order Logic)
Version 1 CSE IIT, Kharagpur
Lesson 15
Inference in FOL - I
Version 1 CSE IIT, Kharagpur
6.2.8 Resolution
We have introduced the inference rule Modus Ponens. Now we introduce another inferenc
Module 6
Knowledge Representation and Logic (First Order Logic)
Version 1 CSE IIT, Kharagpur
Lesson 14
First Order Logic - II
Version 1 CSE IIT, Kharagpur
6.2.5 Herbrand Universe
It is a good exercise to determine for given formulae if they are satisfied/
Module 6
Knowledge Representation and Logic (First Order Logic)
Version 1 CSE IIT, Kharagpur
6.1 Instructional Objective
Students should understand the advantages of first order logic as a knowledge representation language Students should be able to conv
Module 4
Constraint satisfaction problems
Version 1 CSE IIT, Kharagpur
Lesson 10
Constraint satisfaction problems - II
Version 1 CSE IIT, Kharagpur
4.5 Variable and Value Ordering
A search algorithm for constraint satisfaction requires the order in which