Pre Request

The topics included in this cdga training course are related to Probability Theorem and Linear Algebra. Therefore, a basic knowledge of statistics and mathematics will be an added advantage for participants wanting to take this course.

By completing this cdga training course, the candidates will:

• Learn how Artificial Intelligence can be optimized so that maximum potential could be obtained
• Learn how the codes are generated and combined and what these code lines mean
• Understand the procedure of building the Artificial Intelligence
• Learn how to build Artificial Intelligence that is adaptable to any environment in real life
• Be able to identify potential areas of applications of Artificial Intelligence
• Obtain basic ideas and techniques in the design of intelligent computer systems
• Learn statistical and decision-theoretic modeling paradigm
• Know how to build agents that exhibit reasoning and learning
• Be able to apply regression, classification, clustering, retrieval, recommender systems, and deep learning

The target audience for this Artificial Intelligence training course includes business decision-makers, marketing staff, and professionals who are interested in learning robotics, biometrics, and other competing technologies. This CDGA training course is also designed for people who are very keen about learning Artificial Intelligence and applying its awesome result and implementation.

Day 1: Overview of Artificial Intelligence

• Introduction to Artificial Intelligence
• Representation and Search: State Space Search
• State Space Search
• Graph theory and information of state-space search
• Problem-Solving through state-space search
• DFS and BFS algorithms
• Backtracking algorithms
• Workshop 1: Building a state space of some problems

Day 2: Representation and Search: Heuristic Search

• Heuristic search overview
• Pure Heuristic Search
• A* Algorithm
• Iterative- Deepening A*
• Heuristic Path Algorithm
• Simple hill climbing
• Min Max algorithm
• Alpha-beta pruning
• Workshop 2: Building an intelligent X-O gamer

Day 3: Logics and Reasoning

• Logic reasoning overview
• First Order Predicate (FOP)
• Modus ponens and Modus tollens
• Unification and deduction process
• Resolution
• Machine Learning
• Machine learning overview
• Clustering and classification algorithms
• Workshop 3: Building Search Intelligent Agents

Day 4: Decision Making

• Intelligent agent
• Generic agent
• Autonomous agent
• Reflex agent
• Goal-based agent
• Utility-based agent
• Decision theory
• Decision network
• Reinforcement learning
• Markov Decision Processes (MDP)
• Dynamic Decision Networks (DDN)
• Workshop 4: Building Search Intelligent Agents

Day 5: GAS, ANN and Fuzzy Logic

• Genetic Algorithms
• GAS and optimization
• Chromosome and problem coding
• Which problems are more suitable for Gas
• Why GAS has a success story
• ANN
• NN background
• Why the NN model is good
• When to use ANN
• Examples for ANN
• OCR as ANN
• Fuzzy Logic
• Fuzziness vs Probability
• Fuzzy set and membership
• Fuzzy controller
• Fuzzy speed control example
•  Workshop 5: Building a fuzzy logic application

CDGA attendance certificate will be issued to all attendees completing minimum of 75% of the total course duration.