ARTIFICIAL INTELLIGENCE COURSE CANADA

• History of artificial intelligence
• Detailed explanation of Artificial intelligence with a definition and meaning.
• Why artificial intelligence is important in today’s world?
• What is involved in artificial intelligence?
• The academic disciplines which are related to artificial intelligence.

Intelligent Agents

• 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

• Introduction to State Space Search in artificial intelligence, representation.
• Components of search systems.
• The areas where state space search is used.

Graph theory on state space search

• What is a graph theory?
• How may graph theory be used to model problem solving as a search through a graph of problem states?
• The And-Or graph is explained with its uses.
• Introduction on components of the graph theory.

Problem-Solving through state space search

• General Problem, Variants, types of problem-solving approach is explained.

DFS algorithm

• Depth First Search searches deeper into the problem space.
• Advantages, disadvantages and algorithm of depth first search.

DFS with iterative deepening (DFID)

• What iterative deepening search?
• Combination of breadth first search and depth first search.
• Its properties & algorithm along with examples.

Backtracking algorithm

• What is backtracking?
• Implementation of Artificial Intelligence.
• Description of the methods
• When backtracking can be used?
• For what applications backtracking algorithm can be used.?

Simple hill climbing

• Simple Hill Climbing technique in Heuristic search.
• Function optimization of hill climbing.
• Problems with simple hill climbing and its example.

Best-first search algorithm

• Combined advantages of breadth first and depth first searches.

• Heuristic search: Rule of thumb
• Heuristic search: Search strategies.

function of the nodes and the goals.

• The general meaning and the technical meaning of Heuristic search.
• Heuristic search: Function of the nodes and the goals.
• Heuristic search techniques: Pure Heuristic Search
• Heuristic search techniques: A* Algorithm
• Heuristic search techniques: Iterative- Deepening A*
• Heuristic search techniques: Depth First Branch and Bound
• Heuristic search techniques: Heuristic Path Algorithm
• Heuristic search techniques: Recursive Best-First Search

Admissibility Heuristic

• What is admissibility?
• Heuristic, its formulation, construction
• Admissible heuristic using a puzzle problem.
• How to estimate the cost to reach the goal state?

Min-Max algorithm

• Introduction to the Min-Max algorithm.
• Explanation of the two players MIN and MAX.
• Use of Min-Max Algorithm in two-player games such as Chess and others.
• Introduction to search trees.
• Optimization
• Speeding the algorithm
• Adding alpha beta cut-offs

Alpha-beta pruning

• The Alpha value of the node.
• The beta value of the node.
• Improvements over minimax algorithm.
• Pseudo code and a detailed game example.

• 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

• What is a learning rule?
• How to develop the perceptron learning rule?
• Advantages and disadvantages of the perceptron rule.
• The model of perceptron learning with theory and examples.

The types of neural networks

• single layer perceptron network and multi-layer neuron network
• The perceptron network architecture
• Steps for constructing learning rules
• Linear separable problem
• Back propagation algorithm and learning rule in multi-layer perceptron
• How to calculate back propagation algorithm

Updation of weight

• The weight matrix of perceptron.
• Learning of processing elements related to weight.

Clustering algorithms

• Modeling approaches: Centroid-based.
• Modeling approaches: Hierarchical.
• Class of problem.
• Class of methods.
• Cluster algorithm: k-Means
• Cluster algorithm: k-Medians
• Cluster algorithm: Expectation Maximisation
• Cluster algorithm: Hierarchical clustering

For more details Click here!

• What is production system?
• Components of AI production system.
• Four classes of production system.
• Advantages and disadvantages of production system.
• Rules and commands of production system.
• Data driven search.
• Goal driven search.
• Its differences.

CLIPS installation and CLISP Training/Tutorial (ai programing language)

• What is CLIPS?
• What are expert systems?
• History of CLIPS
• Facts and Rules
• Components of CLIPS
• Variables and Pattern matching
• Defining classes and instances
• Wildcard matching
• Field constraints
• Mathematical operators
• Truth and control tutorial

• Generic agent.
• Autonomous agent.
• Reflex agent.
• Goal based agent.
• Utility based agent.

Utility theory

• Utility functions.
• Maximize expected utility.
• Basis of utility theory.
• Six axioms of utility theory.

Decision theory

• Introduction to decision theory.
• Perspectives and disciplines of decision science.
• A few different decision theory also explained

Decision network

• Graphical representation of a decision problem.

Reinforcement learning

• 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?
• The limitations of reinforcement learning.

Markov Decision Processes (MDP)

• Objectives.
• Functions.
• Models.
• Dynamic programming.
• Linear programming.

Dynamic Decision Networks (DDN)

• Features.
• Representations.
• Components.
• DDN is a feature based extension of MDP.

• 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
• Basic concepts.

Probability distribution

• Joint probability distribution.

Bayesian rule for conditional probability

• What is Bayes’ theorem
• How to calculate conditional probability using Bayes’ theorem?