Artificial Intelligence Introduction
Definitions: Artificial Intelligence, Intelligence, Intelligent behavior, Understanding AI, Hard or Strong AI, Soft or Weak AI, Cognitive Science.
Goals of AI: General AI Goal, Engineering based AI Goal, Science-based AI Goal.
AI Approaches: Cognitive science, Laws of thought, Turing Test, Rational agent.
AI Techniques: Techniques that make the system behave as Intelligent, Describe and match, Goal reduction, Constraint satisfaction, Tree Searching, Generate and test, Rule-based systems.
Biology-inspired AI Techniques: Neural Networks, Genetic Algorithms, Reinforcement learning.
Branches of AI: Logical AI, Search in AI, Pattern Recognition, Knowledge Representation, Inference, Commonsense knowledge and reasoning, Learning, Planning, Epistemology, Ontology, Heuristics, Genetic programming.
Applications of AI: Game playing, Speech Recognition, Understanding Natural Language, Computer Vision, Expert Systems.
Problem Solving, Search Strategies
General Problem Solving Problem solving definitions: problem space, problem-solving, state space, state change, the structure of state space, problem solution, problem description; Examples of problem definition.
Search and Control Strategies Search related terms: algorithm’s performance and complexity, computational complexity, “Big – O” notations, tree structure, stacks, and queues; Search: search algorithms, hierarchical representation, search space, the formal statement, search notations, estimate cost, and heuristic function; Control strategies: strategies for search, forward and backward chaining.
Exhaustive Searches Depth-first search Algorithm; Breadth-first search Algorithm; Compare depth-first and breadth-first search;
Heuristic Search Techniques Characteristics of heuristic search; Heuristic search compared with another search; Example of heuristic search; Types of heuristic search algorithms
Constraint Satisfaction Problems (CSPs) and Models Examples of CSPs; Constraint Satisfaction Models: Generate and Test, Backtracking algorithm, Constraint Satisfaction Problems (CSPs): definition, properties, and algorithms.
Knowledge Representation
Knowledge Representation Introduction – Knowledge Progression, KR model, category: typology map, type, relationship, framework, mapping, forward & backward representation, KR system requirements; KR schemes – relational, inheritable, inferential, declarative, procedural; KR issues – attributes, relationship, granularity.
KR Using Predicate Logic Logic as language; Logic representation: Propositional logic, statements, variables, symbols, connective, truth value, contingencies, tautologies, contradictions, antecedent, consequent, argument; Predicate logic – predicate, logic expressions, quantifiers, formula; Representing “IsA” and “Instance” relationships; Computable functions and predicates; Resolution.
KR Using Rules Types of Rules – declarative, procedural, meta-rules; Procedural versus declarative knowledge & language; Logic programming – characteristics, statement, language, syntax & terminology, Data components – simple & structured data objects, Program Components – clause, predicate, sentence, subject, queries; Programming paradigms – models of computation, imperative model, functional model, logic model; Reasoning – Forward and backward chaining, conflict resolution; Control knowledge.
Reasoning System
Reasoning: Definitions Reasoning, formal logic, and informal logic, uncertainty, monotonic logic, non-monotonic Logic; Methods of reasoning and examples – deductive, inductive, abductive, analogy; Sources of uncertainty; Reasoning and KR; Approaches to reasoning – symbolic, statistical, and fuzzy.
Symbolic Reasoning: Non-monotonic reasoning – Default Reasoning, Circumscription, Truth Maintenance Systems; Implementation issues.
Statistical Reasoning: Glossary of terms; Probability and Bayes’ theorem – probability, Bayes’ theorem, examples; Certainty factors rule-based systems; Bayesian networks and certainty factors – Bayesian networks; Dempster Shafer theory – model, belief and plausibility, calculus, combining beliefs; Fuzzy logic – description, membership.
Game Theory
Overview Definition of Game, Game theory, Relevance of Game theory and Game plying, Glossary of terms – Game, Player, Strategy, Zero-Sum game, Constant-Sum game, Nonzero-Sum game, Prisoner’s dilemma, N-Person Game, Utility function, Mixed strategies, Expected payoff, Mini-Max theorem, Saddle point; Taxonomy of games.
Mini-Max Search Procedure Formalizing game: General and a Tic-Tac-Toe game, Evaluation function; MINI-MAX Technique: Game Trees, Mini-Max algorithm.
Game Playing with Mini-Max Example: Tic-Tac-Toe – Moves, Static evaluation, Back-up the evaluations, Evaluation obtained.
Alpha-Beta Pruning Alpha-cutoff, Beta-cutoff
Learning System
What is Learning Definition, learning agents, components of the learning system; Paradigms of machine learning.
Rote Learning Learning by memorization, Learning something by repeating.
Learning from Example: Induction Winston’s learning, Version spaces -learning algorithm (generalization and specialization tree), Decision trees – ID3 algorithm.
Explanation Based Learning (EBL) General approach, EBL architecture, EBL system, Generalization problem, Explanation structure.
Discovery Theory drove – AM system, Data-driven – BACON system
Clustering Distance functions, K-mean clustering – algorithm.
Analogy: Neural net and Genetic Learning Neural Net – Perceptron; Genetic learning – Genetic Algorithm.
Reinforcement Learning RL Problem: Agent – environment interaction, key Features; RL tasks, Markov system, Markov decision processes, Agent’s learning task, Policy, Reward function, Maximize reward, Value functions.
Expert Systems
Introduction Expert system components and human interfaces, expert system characteristics, expert system features.
Knowledge Acquisition Issues and techniques.
Knowledge Base Representing and using domain knowledge – IF-THEN rules, semantic network, frames.
Working Memory
Inference Engine Forward chaining – data-driven approach, backward chaining – goal-driven approach, tree searches – DFS, BFS.
Expert System Shells Shell components and description.
Explanation Example, types of explanation
Application of Expert Systems
Neural Networks
Introduction Why neural network ?, Research history, Biological neuron model, Artificial neuron model, Notations, Functions.
Model of Artificial Neuron McCulloch-Pitts Neuron Equation, Artificial neuron – basic elements, Activation functions – threshold function, piecewise linear function, sigmoidal function.
Neural Network Architectures Single-layer feed-forward network, Multilayer feed-forward network, Recurrent networks.
Learning Methods in Neural Networks Classification of learning algorithms, Supervised learning, Unsupervised learning, Reinforced learning, Hebbian Learning, Gradient descent learning, Competitive learning, Stochastic learning.
Single-Layer NN System Single-layer perceptron: learning algorithm for training, linearly separable task, XOR Problem, learning algorithm; ADAptive LINear Element (ADALINE): architecture, training mechanism
Applications of Neural Networks Clustering, Classification/pattern recognition, Function approximation, Prediction systems.
Fundamentals of Genetic Algorithms
Introduction Why genetic algorithms, Optimization, Search optimization algorithm; Evolutionary algorithm (EAs); Genetic Algorithms (GAs): Biological background, Search space, Working principles, Basic genetic algorithm, Flow chart for Genetic programming.
Encoding Binary Encoding, Value Encoding, Permutation Encoding, and Tree Encoding.
Operators of Genetic Algorithm Reproduction or selection: Roulette wheel selection, Boltzmann selection; fitness function; Crossover: one-Point crossover, two-Point crossover, uniform crossover, arithmetic, heuristic; Mutation: flip bit, boundary, non-uniform, uniform, Gaussian.
Basic Genetic Algorithm Solved examples: maximize function f(x) = x2 and two bar pendulum.
Natural Language Processing
Introduction Natural language: Definition, Processing, Formal language, Linguistic and language processing, Terms related to linguistic analysis, Grammatical structure of utterances – sentence, constituents, phrases, classifications, and structural rules.
Syntactic Processing: Context-free grammar (CFG) – Terminal, Non-terminal, and start symbols; Parser.
Semantic and Pragmatic
AI Common Sense
Introduction Common sense knowledge and reasoning, How to teach commonsense to a computer.
Formalization of Common Sense Reasoning Initial attempts of late 60’s and early, Renewed attempts in late 70’s and 80’s to recent times.
Physical World Modeling the qualitative world, Reasoning with qualitative information.
Common Sense Ontologies Time, Space, Material.
Memory Organization Short term memory (STM), Long term memory (LTM)
Artificial Intelligence Books
We have listed the best Artificial Intelligence Reference Books that can help in your AI exam preparation:
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Artificial Intelligence
Artificial Intelligence
Artificial Intelligence: Building Intelligent Systems
Artificial Intelligence: Building Intelligent Systems
Artificial Intelligence: A Guide for Thinking Humans
Artificial Intelligence: A Guide for Thinking Humans
Artificial Intelligence
Artificial Intelligence
Introduction to Artificial Intelligence
Introduction to Artificial Intelligence
Demystifying Artificial intelligence: Simplified AI and Machine Learning concepts for Everyone
Demystifying Artificial intelligence: Simplified AI and Machine Learning concepts for Everyone
Artificial Intelligence: The Insights You Need from Harvard Business Review
Artificial Intelligence: The Insights You Need from Harvard Business Review
Artificial Intelligence PDF Notes FAQs
What is AI Notes PDF?
Artificial Intelligence (AI) is a branch of Science which deals with helping machines find solutions to complex problems in a more human-like fashion. This generally involves borrowing characteristics from human intelligence, and applying them as algorithms in a computer friendly way.
What is the Need for Artificial Intelligence ?
Artificial Intelligence is needed to create expert systems which exhibit intelligent behavior with the capability to learn, demonstrate, explain and advice its users. Helping machines find solutions to complex problems like humans do and applying them as algorithms in a computer-friendly manner.
What are the Applications of Artificial Intelligence ?
The main Applications of Artificial Intelligence (AI) are:
Natural Language Processing
Gaming
Speech Recognition
Vision Systems
Healthcare
Automotive
What are some examples of Artificial Intelligence ?
Some examples of Artificial Intelligence (AI) are:
Google’s AI-Powered Predictions
Ridesharing Apps Like Uber and Lyft
Email spam Filters & Categorization
Plagiarism Checkers
Mobile Check Deposits
Fraud Prevention
Credit Decisions
Online shopping recommendations
Voice-to-texts
Smart Personal Assistants
What are the branches of Artificial Intelligence ?
The main branches of Artificial Intelligence are:
Perception - understanding images, audio, etc.
Reasoning - answering questions from data
Planning - inferring the required steps to reach a goal
Motion - moving a robot in an environment
Natural language processing - understanding human language
Where can Artificial Intelligence (AI) be used ?
Artificial intelligence (AI) can be used in many sectors such as transportation, finance, healthcare, banking etc.
Smartphones
Smart cars and Drones
Social Media Feeds
Music and Media Streaming Services
Video Games
Online Ads Network
Navigation and Travel
Banking and Finance
What are the problems in Artificial Intelligence ?
The major problems in Artificial Intelligence are:
Threat to Privacy
Threat to Human Dignity
Threat to Safety
