1000+ Unique Technologies Projects Delivered | 500+ Corporate Customers Worldwide | 50000+ Professionals Trained on 40+ Domains in Over 30 Countries | Just Launched B2I Offerings | Live, Instructor-led.

Artificial Intelligence

This web-based training course on Artificial Intelligence , administration and development, is available online to all individuals, institutions, corporates and enterprises in India (New Delhi NCR, Bangalore, Chennai, Kolkatta), US, UK, Canada, Australia, Singapore, United Arab Emirates (UAE), China and South Africa. No matter where you are located, you can enroll for any training with us - because all our training sessions are delivered online by live instructors using interactive, intensive learning methods.


Reviews , Learners(390)



Course Details

This course helps trainees to learn speech recognition, face recognition, machine translation, autonomous driving and automatic scheduling. This technique is becoming popular because a human being does not do any work by itself but it just passes a command to complete the work. These are basically real world problems and the main goal of AI is to tackle these problems more emphatically. The main idea of the course is to help trainees to deal with the tools to tackle AI problems that might encounter in life. This training program comes with a bunch of elements such as to define AI, problem solving, knowledge and reasoning, uncertain knowledge and reasoning. With the help of this training program trainees will further learn natural language processing, natural language for communication, perception and robotic.

Introduction

  • Define AI
  • Fundamentals of Artificial Intelligence
  • History of Artificial Intelligence
  • State of Art

Intelligent Agents

  • Agents and Environments for AI
  • Good Behavior: Fundamentals of Rationality
  • Environments Nature
  • Agents Structure

To Solve the Problem

Solving Problems by Searching

  • Agents for Problem Solving
  • Example of Problems
  • To search for Solutions
  • Search Strategies : Uninformed
  • Search Strategies : Informed (Heuristic)
  • Functions of Informed (Heuristic)

Go Beyond Classical Search

  • Local Search Algorithms and to Optimize Problems
  • Local Search in Continuous Spaces
  • To search with Nondeterministic Actions
  • To search with Partial Observations
  • Unknown Environments and Online Search Agents

The Adversarial Search

  • For Games
  • To take Optimal Decisions in Games
  • Alpha and Beta Pruning
  • Imperfect Real-Time Decisions
  • Stochastic Games
  • Partially Observed Games
  • Programs for State of the Art Game

Constraint Satisfaction Problems (CSPs)

  • To Define Constraint Satisfaction Problems
  • Propagation of Constraint: Inference in CSPs
  • Backtracking Searching for CSPs
  • Local Searching for CSPs
  • The Construction of Problems

Knowledge, Planning and Reasoning

Logical Agents

  • Agents based on Knowledge
  • The Wumpus World
  • Logic Required
  • Propositional Logic: A Very Simple Logic
  • Propositional Theorem
  • Effective Checking of Propositional Model
  • Propositional Logic Based Agents

First Order Logic

  • Revisiting of Representation
  • Syntax and Semantics
  • To Use First Order Logic
  • Knowledge Required in First-Order Logic

Speculation in First Order Logic

  • Differentiate in Propositional and First-Order Inference
  • Lifting and Unification
  • Chaining Forward
  • Chaining Backward
  • The Resolution

Classical Planning

  • Classical Planning Defined
  • Algorithms to Plan as State-Space Search
  • Planning Graphical Representation
  • Other Classical Planning Approaches
  • To Analyze Planning Approaches

To Plan and Act in the Real World

  • Time, Schedules, Resources
  • Hierarchical Planning
  • To Plan and Act in Nondeterministic Domains
  • Multi-agent Planning

To Represent Knowledge

  • Ontological Engineering
  • Objects and Categories
  • Types of Events
  • Mental Objects and Mental Events
  • Reasoning Systems for Categories
  • Reasoning using Default Information
  • The E-Commerce and Internet Shopping World

Uncertain Knowledge and Reasoning

To Quantify Uncertainty

  • To Act under Uncertainty
  • The Basic Probability Notation
  • Inference with the help of Full Joint Distributions
  • Independence
  • Bayes' Rule and Its Usage
  • Revisited Wumpus World

Probabilistic Reasoning

  • To Represent Knowledge in an Uncertain Domain
  • The Semantics of Bayesian Networks
  • Efficient way for Representation of Conditional Distributions
  • Exact Inference in Bayesian Networks
  • Approximate Inference in Bayesian Networks
  • Relational and First-Order Probability Models
  • Other Approaches for Uncertain Reasoning

Probabilistic Reasoning over Time

  • Time and Uncertainty
  • Inference in Temporal Models
  • Hidden Markov Models
  • Filters such as Kalman
  • Bayesian Networks
  • To Keep Track of Many Objects

To Make Simple Decisions

  • Combining Beliefs and Desires under Uncertainty
  • The Basis of Utility Theory
  • Utility Functions
  • Multi-attribute Utility Functions
  • Decision Networks
  • The Value of Information
  • Decision-Theoretic Expert Systems

To Make Complex Decisions

  • Sequentially Decision the Problems
  • Value Iteration
  • Iteration of Policy
  • Partially Observable MDPs
  • To make Decisions with Multiple Agents such as :Game Theory
  • To Design a Mechanism

Learning

Learning from Examples

  • Different Forms of Learning
  • Supervised Learning
  • To Learn the Decision Trees
  • To Evaluate and choose the Best Hypothesis
  • The Learning Theory
  • Regression and Classification by using Linear Models
  • Artificial Neural Networks
  • Nonparametric Models
  • To Support Vector Machines
  • To Ensemble Learning Process
  • To Impart Practical Machine Learning

Knowledge in Learning

  • Logical Formulation of Learning
  • Knowledge required for Learning
  • Explanation Based Learning
  • To Learn Using Relevance Information
  • To learn Inductive Logic Programming

Learning Probabilistic Models

  • Statistical Learning
  • To Learn with Complete Data
  • To Learn with Hidden Variables: The EM Algorithm

Reinforcement Learning (RL)

  • Introduction
  • Passive RL
  • Active RL
  • Generalization in RL
  • Search Policy
  • Applications of RL

Communicating, Perceiving, and Acting

Natural Language Processing

  • Different Language Models
  • Classification of Text
  • Retrieval of Information
  • Extraction of Information

Natural Language for Communication

  • Phrase Structure Grammars
  • Syntactic Analysis
  • Augmented Grammars and Semantic Interpretation
  • Translation of Machine
  • Recognition of Speech

Perception

  • Formation of Image
  • Early stage Image Processing Operations
  • To Recognize Objects by Appearance
  • To Reconstructing the 3D World
  • Object Recognition from Structural Information
  • Use the Vision

Robotics

  • Introduction to Robotics
  • Hardware required for Robot
  • Robotic Perception
  • Plan to Move
  • To Plan Uncertain Movements
  • Moving
  • Software Architectures for Robotic
  • Applications

Conclusions

Philosophical Foundations

  • Weak AI: Can Machines Act Intelligently?
  • Strong AI: Can Machines Really Think like Human?
  • The types of Risks for Developing Artificial Intelligence

AI: The Present and Future

  • Components of Agent
  • Architectures of Agent
  • Are we really following the Right Direction?

Our Clients

B2B Technical Trainings Projects Delivered


Read More