Artificial Intelligence and Applications - TRAINING


Contents at a Glance

• Introduction
• Intelligent Agents
• Informed Search Methods
• Game Playing
• Knowledge and reasoning
• Agents that Reason Logically
• First-Order Logic
• Building a Knowledge Base
• Inference in First-Order Logic
• Logical Reasoning Systems
• Acting logically
• Planning
• Practical Planning
• Planning and Acting
• Uncertain knowledge and reasoning
• Uncertainty
• Probabilistic Reasoning Systems
• Making Simple Decisions
• Making Complex Decisions
• Learning
• Learning from Observations
• Learning in Neural and Belief Networks
• Reinforcement Learning
• Knowledge in Learning
• Communicating, perceiving, and acting
• Agents that Communicate
• Practical Natural Language Processing
• Perception
Robotics

Course Objectives

Since the invention of computers or machines, their capability to perform various tasks went on growing exponentially. Humans have developed the power of computer systems in terms of their diverse working domains, their increasing speed, and reducing size with respect to time.
A branch of Computer Science named artificial intelligence pursues creating the computers or machines as intelligent as human beings.
According to the father of artificial intelligence John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”.
Artificial intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think.
AI is accomplished by studying how human brain thinks, and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems. While exploiting the power of the computer systems, the curiosity of human, lead him to wonder, “Can a machine think and behave like humans do?”
Thus, the development of AI started with the intention of creating similar intelligence in machines that we find and regard high in humans.
Goals of AI
• To Create Expert Systems
: The systems which exhibit intelligent behavior, learn, demonstrate, explain, and advice its users.
• To Implement Human Intelligence in Machines: Creating systems that understand, think, learn, and behave like humans.

Artificial Intelligence and Applications Training Course - OUTLINES


Introduction

• What is AI?
• Acting humanly: The Turing Test approach
• Thinking humanly: The cognitive modelling approach
• Thinking rationally: The laws of thought approach
• Acting rationally: The rational agent approach
• The Foundations of artificial intelligence
• Philosophy (428 B.C.-present)
• Mathematics (c. 800-present)
• Psychology (1879-present)
• Computer engineering (1940-present)
• Linguistics (1957-present)
• The History of artificial intelligence
• The gestation of artificial intelligence (1943-1956)
• Early enthusiasm, great expectations (1952-1969)
• A dose of reality (1966-1974)
• Knowledge-based systems: The key to power? (1969-1979)
• AI becomes an industry (1980-1988)
• The return of neural networks (1986-present)
• Recent events (1987-present)
• The State of the Art

Intelligent Agents

• Introduction
• How Agents Should Act
• The ideal mapping from percept sequences to actions
• Autonomy
• Structure of Intelligent Agents
• Agent programs
• Why not just look up the answers?
• An example
• Simple reflex agents
• Agents that keep track of the world
• Goal-based agents
• Utility-based agents
• Environments
• Properties of environments
• Environment programs

Problem-solving

• Solving Problems by Searching
• Problem-Solving Agents
• Formulating Problems
• Knowledge and problem types
• Well-defined problems and solutions
• Measuring problem-solving performance
• Choosing states and actions
• Toy problems
• Real-world problems
• Searching for Solutions
• Generating action sequences
• Data structures for search trees
• Search Strategies
• Breadth-first search
• Uniform cost search
• Depth-first search
• Depth-limited search
• Iterative deepening search
• Bidirectional search
• Comparing search strategies
• Avoiding Repeated States
• Constraint Satisfaction Search

Informed Search Methods

• Best-First Search
• Minimize estimated cost to reach a goal: Greedy search
• Minimizing the total path cost: A* search
• Heuristic Functions
• The effect of heuristic accuracy on performance
• Inventing heuristic functions
• Heuristics for constraint satisfaction problems
• Memory Bounded Search
• Iterative deepening A* search (IDA*)
• SMA* search
• Iterative Improvement Algorithms
• Hill-climbing search
• Simulated annealing
• Applications in constraint satisfaction problems

Game Playing

• Introduction: Games as Search Problems
• Perfect Decisions in Two-Person Games
• Imperfect Decisions
• Evaluation functions
• Cutting off search
• Alpha-Beta Pruning
• Effectiveness of alpha-beta pruning
• Games That Include an Element of Chance
• Position evaluation in games with chance nodes
• Complexity of expectiminimax
• State-of-the-Art Game Programs
• Chess
• Checkers or Draughts
• Othello
• Backgammon

Knowledge and reasoning - Agents that Reason Logically

• A Knowledge-Based Agent
• The Wumpus World Environment
• Specifying the environment
• Acting and reasoning in the wumpus world
• Representation, Reasoning, and Logic
• Representation
• Inference
• Logics
• Prepositional Logic: A Very Simple Logic
• Syntax
• Semantics
• Validity and inference
• Models
• Rules of inference for propositional logic
• Complexity of prepositional inference
• An Agent for the Wumpus World
• The knowledge base
• Finding the wumpus
• Translating knowledge into action
• Problems with the propositional agent

First-Order Logic

• Syntax and Semantics
• Terms
• Atomic sentences
• Complex sentences
• Quantifiers
• Equality
• Extensions and Notational Variations
• Higher-order logic
• Functional and predicate expressions using the A operator
• The uniqueness quantifier 3!
• The uniqueness operator /
• Notational variations
• Using First-Order Logic
• The kinship domain
• Axioms, definitions, and theorems
• The domain of sets
• Special notations for sets, lists and arithmetic
• Asking questions and getting answers
• Logical Agents for the Wumpus World
• A Simple Reflex Agent
• Limitations of simple reflex agents .
• Representing Change in the World
• Situation calculus
• Keeping track of location
• Deducing Hidden Properties of the World
• Preferences Among Actions
• Toward a Goal-Based Agent

Building a Knowledge Base

• Properties of Good and Bad Knowledge Bases
• Knowledge Engineering
• The Electronic Circuits Domain
• Decide what to talk about
• Decide on a vocabulary
• Encode general rules
• Encode the specific instance
• Pose queries to the inference procedure
• General Ontology
• Representing Categories
• Measures
• Composite objects
• Representing change with events
• Times, intervals, and actions
• Objects revisited
• Substances and objects
• Mental events and mental objects
• Knowledge and action
• 8.5 The Grocery Shopping World
• Complete description of the shopping simulation
• Organizing knowledge
• Menu-planning
• Navigating
• Gathering
• Communicating
• Paying

Inference in First-Order Logic

• Inference Rules Involving Quantifiers
• An Example Proof
• Generalized Modus Ponens
• Canonical form
• Unification
• Sample proof revisited
• Forward and Backward Chaining
• Forward-chaining algorithm
• Backward-chaining algorithm
• Completeness
• Resolution: A Complete Inference Procedure
• The resolution inference rule
• Canonical forms for resolution
• Resolution proofs
• Conversion to Normal Form
• Example proof
• Dealing with equality
• Resolution strategies
• Completeness of resolution

Logical Reasoning Systems

• Introduction
• Indexing, Retrieval, and Unification
• Implementing sentences and terms
• Store and fetch
• Table-based indexing
• Tree-based indexing
• The unification algorithm
• Logic Programming Systems
• The Prolog language
• Implementation
• Compilation of logic programs
• Other logic programming languages
• Advanced control facilities
• Theorem Provers
• Design of a theorem prover
• Extending Prolog
• Theorem provers as assistants
• Practical uses of theorem provers
• Forward-Chaining Production Systems
• Match phase
• Conflict resolution phase
• Practical uses of production systems
• Frame Systems and Semantic Networks
• Syntax and semantics of semantic networks
• Inheritance with exceptions
• Multiple inheritance
• Inheritance and change
• Implementation of semantic networks
• Expressiveness of semantic networks
• Description Logics
• Practical uses of description logics
• Managing Retractions, Assumptions, and Explanations

Acting logically - Planning

• A Simple Planning Agent
• From Problem Solving to Planning
• Planning in Situation Calculus
• Basic Representations for Planning
• Representations for states and goals
• Representations for actions
• Situation space and plan space
• Representations for plans
• A Partial-Order Planning Example
• A Partial-Order Planning Algorithm
• Planning with Partially Instantiated Operators
• Knowledge Engineering for Planning
• The blocks world
• Shakey's world

Practical Planning

• Practical Planners
• Spacecraft assembly, integration, and verification
• Job shop scheduling
• Scheduling for space missions
• Buildings, aircraft carriers, and beer factories
• Hierarchical Decomposition
• Extending the language
• Modifying the planner
• Analysis of Hierarchical Decomposition
• Decomposition and sharing
• Decomposition versus approximation
• More Expressive Operator Descriptions
• Conditional effects
• Negated and disjunctive goals
• Universal quantification
• A planner for expressive operator descriptions
• Resource Constraints
• Using measures in planning
• Temporal constrains

Planning and Acting

• Conditional Planning
• The nature of conditional plans
• An algorithm for generating conditional plans
• Extending the plan language
• A Simple Replanning Agent
• Simple replanning with execution monitoring
• Fully Integrated Planning and Execution
• Comparing conditional planning and replanning
• Coercion and abstraction

Uncertainty

• Acting under Uncertainty
• Handling uncertain knowledge
• Uncertainty and rational decisions
• Design for a decision-theoretic agent
• Basic Probability Notation
• Prior probability
• Conditional probability
• The Axioms of Probability
• Why the axioms of probability are reasonable
• The joint probability distribution
• Bayes' Rule and Its Use
• Applying Bayes' rule: The simple case
• Normalization
• Using Bayes' rule: Combining evidence
• Where Do Probabilities Come From?

Probabilistic Reasoning Systems

• Representing Knowledge in an Uncertain Domain
• The Semantics of Belief Networks
• Representing the joint probability distribution
• Conditional independence relations in belief networks
• Inference in Belief Networks
• The nature of probabilistic inferences
• An algorithm for answering queries
• Inference in Multiply Connected Belief Networks
• Clustering methods
• Cutset conditioning methods
• Stochastic simulation methods
• Knowledge Engineering for Uncertain Reasoning
• Case study: The Pathfinder system
• Other Approaches to Uncertain Reasoning
• Default reasoning
• Rule-based methods for uncertain reasoning
• Representing ignorance: Dempster-Shafer theory
• Representing vagueness: Fuzzy sets and fuzzy logic

Making Simple Decisions

• Combining Beliefs and Desires Under Uncertainty
• The Basis of Utility Theory
• Constraints on rational preferences
• Utility Functions
• The utility of money
• Utility scales and utility assessment
• Multiattribute utility functions
• Dominance
• Preference structure and multiattribute utility
• Decision Networks
• Representing a decision problem using decision networks
• Evaluating decision networks
• The Value of Information
• A simple example
• A general formula
• Properties of the value of information
• Implementing an information-gathering agent
• Decision-Theoretic Expert Systems

Making Complex Decisions

• Sequential Decision Problems
• Value Iteration
• Policy Iteration
• Decision-Theoretic Agent Design
• The decision cycle of a rational agent
• Sensing in uncertain worlds
• Dynamic Belief Networks
• Dynamic Decision Networks

Learning - Learning from Observations

• A General Model of Learning Agents
• Components of the performance element
• Representation of the components
• Available feedback
• Prior knowledge
• Bringing it all together
• Inductive Learning
Learning Decision Trees
• Decision trees as performance elements
• Expressiveness of decision trees
• Inducing decision trees from examples
• Assessing the performance of the learning algorithm
• Practical uses of decision tree learning
• Using Information Theory
• Noise and overfilling
• Broadening the applicability of decision Irees
• Learning General Logical Descriptions
• Hypotheses
• Examples
• Current-besl-hypolhesis search
• Least-commitment search
• Why Learning Works: Computational Learning Theory
• How many examples are needed?
• Learning decision lists

Learning in Neural and Belief Networks

• How the Brain Works
• Comparing brains with digital computers
• Neural Networks
• Notation
• Simple computing elements
• Network structures
• Optimal network structure
• Perceptrons
• What perceptrons can represent
• Learning linearly separable functions
• Multilayer Feed-Forward Networks
• Back-propagation learning
• Back-propagation as gradient descent search
• Applications of Neural Networks
• Pronunciation
• Handwritten character recognition
• Driving
• Bayesian Methods for Learning Belief Networks
• Bayesian learning
• Belief network learning problems
• Learning networks with fixed structure
• A comparison of belief networks and neural networks

Reinforcement Learning

• Introduction
• Passive Learning in a Known Environment
• Nai've updating
• Adaptive dynamic programming
• Temporal difference learning
• Passive Learning in an Unknown Environment
• Active Learning in an Unknown Environment
• Exploration
• Learning an Action-Value Function
Generalization in Reinforcement Learning
• Applications to game-playing
• Application to robot control
• Genetic Algorithms and Evolutionary Programming

Knowledge in Learning

• Knowledge in Learning
• Some simple examples
• Some general schemes
• Explanation-Based Learning
• Extracting general rules from examples
• Improving efficiency
• Learning Using Relevance Information
• Determining the hypothesis space
• Learning and using relevance information
• Inductive Logic Programming
• An example
• Inverse resolution
• Top-down learning methods

Communicating, perceiving, and acting - Agents that Communicate

• Communication as Action
• Fundamentals of language
• The component steps of communication
• Two models of communication
• Types of Communicating Agents
• Communicating using Tell and Ask
• Communicating using formal language
• An agent that communicates
• A Formal Grammar for a Subset of English
• The Lexicon of £o
• The Grammar of £Q
• Syntactic Analysis (Parsing)
• Definite Clause Grammar (DCG)
• Augmenting a Grammar
• Verb Subcategorization
• Generative Capacity of Augmented Grammars
• Semantic Interpretation
• Semantics as DCG Augmentations
• The semantics of "John loves Mary"
• The semantics of £\
• Converting quasi-logical form to logical form
• Pragmatic Interpretation
• Ambiguity and Disambiguation
• Disambiguation
• A Communicating Agent

Practical Natural Language Processing

• Practical Applications
• Machine translation
• Database access
• Information retrieval
• Text categorization
• Extracting data from text
• Efficient Parsing
• Extracting parses from the chart: Packing
• Scaling Up the Lexicon
• Scaling Up the Grammar
• Nominal compounds and apposition
• Adjective phrases
• Determiners
• Noun phrases revisited
• Clausal complements
• Relative clauses
• Handling agrammatical strings
• Ambiguity
• Syntactic evidence
• Lexical evidence
• Semantic evidence
• Metonymy
• Metaphor
• Discourse Understanding
• The structure of coherent discourse

Perception

• Introduction
• Image Formation
• Pinhole camera
• Lens systems
• Photometry of image formation
• Spectrophotometry of image formation
• Image-Processing Operations for Early Vision
• Convolution with linear filters
• Edge detection
• Extracting 3-D Information Using Vision
• Motion
• Binocular stereopsis
• Texture gradients
• Shading
• Contour
• Using Vision for Manipulation and Navigation
• Object Representation and Recognition
• The alignment method
• Using projective invariants
• Speech Recognition
• Signal processing
• Defining the overall speech recognition model
• The language model: P(words)
• The acoustic model: P(signallwords)
• Putting the models together
• The search algorithm
• Training the model

Robotics

• Introduction
• Tasks: What Are Robots Good For?
• Manufacturing and materials handling
• Gofer robots
• Hazardous environments
• Telepresence and virtual reality
• Augmentation of human abilities
• Parts: What Are Robots Made Of?
• Effectors: Tools for action
• Sensors: Tools for perception
• Architectures
• Classical architecture
• Situated automata
• Configuration Spaces: A Framework for Analysis
• Generalized configuration space
• Recognizable Sets
• Navigation and Motion Planning
• Cell decomposition
• Skeletonization methods
• Fine-motion planning
• Landmark-based navigation
• Online algorithms

Philosophical Foundations

• The Big Questions
• Foundations of Reasoning and Perception
• On the Possibility of Achieving Intelligent Behavior
• The mathematical objection
• The argument from informality
• Intentionality and Consciousness
• The Chinese Room
• The Brain Prosthesis Experiment

AI: Present and Future

• Have We Succeeded Yet?
• What Exactly Are We Trying to Do?
• What If We Do Succeed?
• Complexity analysis and O() notation
• Asymptotic Analysis
• Inherently Hard Problems
• Bibliographical and Historical Notes
• Notes on Languages and Algorithms
• Defining Languages with Backus-Naur Form (BNF)
• Describing Algorithms with Pseudo-Code
• Nondeterminism
• Static variables
• Functions as values
• The Code Repository

Other Information Technology Courses

Documents and Records Management Compliance
Sentiment Analysis and Applications
Informaton Security and Cryptology
Big Data Management
IT Risk Management
Cloud Computing
Data Mining

CONTACT US


Cumhuriyet Cad. No:5
Floor 5 - Taksim
34437 Beyoğlu-Istanbul

inquire@astra-entrepreneurs.com

+90 (553) 743 83 69
You can also reach us via VOIP
Whatsapp, Viber

Do not hesitate to send your inquiry

Copyright © 2017, ASTRA ENTREPRENEURS