Artificial intelligence is the simulation of human intelligence through machines and mostly through computer systems. Artificial intelligence is a sub field of computer. It enables computers to do things which are normally done by human beings. Any program can be said to be Artificial intelligence if it is able to do something that the humans do it using their intelligence. In simple words, Artificial Intelligence means the power of a machine to copy the human intelligent behavior. It is about designing machines that can think.
About Artificial Intelligence
Why is Artificial Intelligence used?
Artificial Intelligence has been used in wide range of fields these days. For example medical diagnosis, robots, remote sensing, etc. Artificial intelligence is around us in many ways but we don’t realize it. For example the ATM which we are using is an artificial intelligence machine. Few of the advantages of using artificial intelligence is listed below
Greater precision and accuracy can be achieved through AI
These machines do not get affected by the planetary environment or atmosphere
Robots can be programmed to do the works which are difficult for the human beings to complete
AI will open up doors to new technological breakthroughs
As they are machines they don’t stop for sleep or food or rest. They just need some source of energy to work Fraud detection becomes easier with artificial intelligence
Using AI the time consuming tasks can be done more efficiently dangerous tasks can be done using AI machines as it affects only the machines and not the human beings.
Call Now- +91-921-276-0556
Send a Query
Artificial Intelligence & Machine Learning Course Objectives
At the end of this course you will be able to
✓ Identify potential areas of applications of AI
✓ Basic ideas and techniques in the design of intelligent computer systems
✓ Statistical and decision–theoretic modelling paradigm
✓ How to build agents that exhibit reasoning and learning
✓Apply regression, classification, clustering, retrieval, recommender systems, and deep learning.
A basic knowledge in statistics and mathematics is an added advantage to take up this course.
The target audience for this course includes students and professionals who are interested in learning robotics and biometrics. This course is also meant for people who are very keen about learning Artificial Intelligence.
Section 1: Overview of Artificial Intelligence
Introduction to Artificial Intelligence
Artificial Intelligence is a branch of science which makes machines to solve the complex problems in a human way. This chapter contains history of artificial intelligence, detailed explanation of Artificial intelligence with a definition and meaning. It also explains why artificial intelligence is important in today’s world, what is involved in artificial intelligence and the academic disciplines which are related to artificial intelligence.
This section will help you to learn what is intelligent agents, agents and environment, concept of rationality, types of agents – Generic agent, Autonomous agent, Reflex agent, Goal Based Agent, Utility based agent. The basis of classification of the agents are also explained in detail. The types of environment are also explained with examples.
Section 2: Representation and Search: State Space Search
Information on State Space Search
This chapter gives a brief introduction to State Space Search in artificial intelligence, its representation, components of search systems and the areas where state space search in used.
Graph theory on state space search
Under this chapter you will learn what is a graph theory and how it may be used to model problem solving as a search through a graph of problem states. The And/or graph is explained with its uses. The components of the graph theory is also given a brief introduction.
Problem Solving through state space search
The topics included in this section includes General Problem, Variants, types of problem solving approach is explained with examples.
Depth First Search searches deeper into the problem space. This section also includes the advantages, disadvantages and algorithm of depth first search.
DFS with iterative deepening (DFID)
This is a combination of breadth first search and depth first search. In this section you will learn what is iterative deepening search, its properties and algorithm along with examples.
Backtracking is an implementation of Artificial Intelligence. This section explains what is backtracking, description of the method, when backtracking can be used and for what applications backtracking algorithm can be used. It is explained with few examples and graphs.
Section 3: Representation and Search : Heuristic Search
Heuristic search overview
Heuristic search is an search technique that employs a rule of thumb for its moves. It plays a major role in search strategies. In this chapter the general meaning and the technical meaning of Heuristic search is explained. It contains more information about the Heuristic search along with the function of the nodes and the goals. The section also contains the following topics which are its type of techniques
Pure Heuristic Search
Iterative- Deepening A*
Depth First Branch and Bound
Heuristic Path Algorithm
Recursive Best-First Search
Simple hill climbing
This chapter explains the Simple Hill Climbing technique in Heuristic search, function optimization of hill climbing, problems with simple hill climbing and its example.
Best first search algorithm
This algorithm combines the advantages of breadth first and depth first searches. This algorithm finds the most promising path. It is explained with examples.
This algorithm is used to estimate the cost to reach the goal state. In this chapter you will learn what is admissibility heuristic, its formulation, construction and examples of admissible heuristic using a puzzle problem.
Min Max algorithm
This algorithm is used in two player games such as Chess and others. This section involves a brief introduction to search trees, introduction to the algorithm, explanation of the two players MIN and MAX, optimization, speeding the algorithm, adding alpha beta cut-offs and an example using a game is given for your easy understanding.
Alpha beta pruning
Alpha beta pruning is a method to reduce the number of nodes in minimax algorithm in its search tree. This chapter explains the Alpha value of the node, Beta value of the node, improvements over minimax algorithm, its Pseudo code and an detailed game example.
Section 4: Machine Learning
Machine learning overview
Machine learning is an applied statistics or mathematics. It is a sub field of computer science. This chapter gives a brief introduction about the Machine learning, history of machine learning, types of problems and tasks in machine learning and its algorithms.
Perceptron learning and Neural networks
In machine learning, perceptron is an algorithm. This chapter starts with an explanation to what a learning rule is and how to develop the perceptron learning rule. The advantages and disadvantages of the perceptron rule is discussed. The model of perceptron learning is explained using the theory and examples.
The types of neural networks – single layer perceptron network and multi-layer neuron network is explained in detail. The perceptron network architecture is explained with few pictures
The steps for constructing learning rules are also given in this chapter.
The linear separable problem is included in this section with examples.
The back propagation algorithm and learning rule in multi-layer perceptron is discussed here. It also explains how to calculate back propagation algorithm in a step by step procedure.
Updation of weight
The weight matrix of perceptron, learning of processing elements with related to weight are included in this chapter.
Clustering methods are organized by modelling approaches like centroid-based and hierarchical. It describes the class of problem and the class of methods. This chapter includes the details of cluster algorithm and its popular algorithms k-Means, k-Medians, Expectation Maximisation and hierarchical clustering with few examples.
Section 5: Logics and Reasoning
Logic reasoning overview
Logic is the study of what follows from what. This section explains the facts about logics in artificial intelligence, why it is useful, the arguments and its logical meanings are explained in detail. Proof theory is used to check the validity of the arguments.
In propositional logic lexicon and grammar are the syntax used and it is explained in detail under this topic along with the symbols used. The theorems, semantics, models and arguments are also mentioned in this chapter.
First Order Predicate calculus (FOPC)
FOPC includes a wide range of entities. The predicate calculus includes variables and constants. The formula for FOPC is defined and each of its symbol is explained in detail with examples.
Modus ponens and Modus tollens
Modus Ponens and Modus tollens are forms of valid inferences. Modus Ponens involves two premises – conditional statement and the affirmation of the antecedent of the conditional statement. Both the terms are explained with examples.
Unification and deduction process
The unification algorithm, its expressions and transactions are given in this chapter
Resolution rules, its meaning, propositional resolution example, power of false and other examples are given in brief in this section.
This chapter explains what is Skolemization, how it works, uses of Skolemization and Skolem theories in detail.
Section 6: Rule Based Programming
This section contains what is production system, components of AI production system, four classes of production system, advantages and disadvantages of production system. It also contains the following topics
Rules and commands of production system
Data driven search
Goal driven search
CLIPS installation and clips tutorial
The topics included in this section are listed below
What is CLIPS ?
What are expert systems ?
History of CLIPS
Facts and Rules
Components of CLIPS
Variables and Pattern matching
Defining classes and instances
Truth and control tutorial
Section 7: Decision Making
This section starts with an brief introduction to intelligent agent. The different types of agents are covered in this topic as mentioned in the list below
Goal based agent
Utility based agent
All these types of agents are explained with a pictorial representation and example.
This section covers the following topics
Maximize expected utility
Basis of utility theory
Six axioms of utility theory
This chapter gives a brief introduction to decision theory, its perspectives and disciplines of decision science. The different decision theory is also explained in detail.
Decision network is a graphical representation of a decision problem. It is discussed in this chapter in detail with examples.
This includes a definition, why reinforcement learning, how does it work, what are the motivations, what technology is used, who uses it, where can the reinforcement learning be applied and the limitations of reinforcement learning.
Markov Decision Processes (MDP)
This section includes the objectives, functions, models, dynamic programming, linear programming and examples.
Dynamic Decision Networks (DDN)
DDN is a feature based extension of MDP. This section explains its features, representations, components along with examples.
Section 8: Stochastic methods
Basics of set theory
Here you will learn the importance of set theory, what is a set, set notation, well defined sets, number sets, set equality, cardinality of a set, subsets and proper subsets and finally power sets. It also includes the basic concepts in set theory.
The joint probability distribution is explained in this section with an example and pictorial representation.
Bayesian rule for conditional probability
This section explains what Bayes’ theorem is and how to calculate conditional probability using Bayes’ theorem. This is explained with few illustrations of college life, medical diagnosis and witness reliability.