人工智慧：搜尋方法與邏輯推論 (Artificial Intelligence - Search & Logic)
- 4.8
-
![]()
![]()
![]()
![]()
![]()
Approx. 19 hours to complete
Course Summary
Learn about the exciting world of Artificial Intelligence and Machine Learning with the Rengong Zhineng course on Coursera.Key Learning Points
- Understand the fundamentals of AI and Machine Learning
- Learn about Neural Networks, Deep Learning, and Natural Language Processing
- Gain hands-on experience with real-world projects
Job Positions & Salaries of people who have taken this course might have
- AI Engineer
- USA: $120,000
- India: ₹1,000,000
- Spain: €50,000
- Machine Learning Scientist
- USA: $150,000
- India: ₹1,500,000
- Spain: €60,000
- Data Scientist
- USA: $125,000
- India: ₹1,200,000
- Spain: €55,000
Related Topics for further study
Learning Outcomes
- Develop a strong foundation in AI and Machine Learning
- Gain practical experience with real-world projects
- Be able to apply AI and Machine Learning techniques to solve real-world problems
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of programming
- Familiarity with statistics and linear algebra
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Machine Learning
- Introduction to Artificial Intelligence
Related Education Paths
Notable People in This Field
- Founder of deeplearning.ai
- Co-Director, Stanford Institute for Human-Centered AI
Related Books
Description
本課程分為人工智慧（上）、人工智慧（下）兩部份，第一部分除了人工智慧概論外，著重在目標搜尋、meta heuristic、電腦對弈、演繹學習（包含證言邏輯、一階邏輯及 planning ）等技術。這些技術主要發展時機為人工智慧的第一波及第二波熱潮，也就是 1950 年代至 1990 年代附近的主流發展，即使到現在也在各個領域廣為應用。
Outline
- Introduction
- 1-1 History of AI：TuringTest and Its Application, Chinese Room Argument
- 1-2 What is AI
- 1-3 Agents and Environments, PEAS, Environment Type
- 1-4 Different Level Of AI
- 1-5 Wave of AI：Debut, Knowledge Driven, Data Driven
- 1-6 The Classification of Agent, First Wave of AI (Artificial Neural Network)
- 1-7 Second Wave of AI (Expert System)
- 1-8 Third Wave of AI (Some Theory and Principle of Machine Learning)
- 1-9 Conclusion of AI and Machine Learning
- NTU MOOC 課程問題詢問與回報機制
- Uninformed search
- 2-1 Problem Solving Agents, Problem Formulation (i)
- 2-2 Problem Formulation (ii) - Abstraction
- 2-3 Search on Tree and Graph
- 2-4 Uninformed Search (i) - Breadth-First Search, Uniform-Cost Search
- 2-5 Uninformed Search (ii) - Depth-First Search, Depth-Limited Search, Iterative-Deepening Search
- 2-6 Uninformed Search (iii) - Iterative-Deepening Search, Bidirectional Search
- Week 2
- Informed search
- 3-1 Best-First Search (i) - Greedy Search
- 3-2 Best-First Search (ii) - A* Search
- 3-3 Best-First Search (iii) - Optimality of A*
- 3-4 Memory Bounded Search (i) - Iterative Deepening A*, RBFS
- 3-5 Memory Bounded Search (ii) - RBFS, Simplified Memory-bounded A*
- 3-6 Heuristic - Preformance, Generating Heuristics
- Week 3
- Non-classic search
- 4-1 Black-Box Optimization
- 4-2 Steepest Descent
- 4-3 Simulated Annealing
- 4-4 Evolutionary Computation
- 4-5 Non-deterministic Actions - AND-OR Search, Partial Observations (i) - Sensor-less
- 4-6 Partial Observations (ii) - With Sensors
- 4-7 Partial Observations (iii) - Unknown Environments
- Week 4
- Adversarial search
- 5-1 Type of Games - Symbols, Game Tree
- 5-2 Optimal Decision, Negamax Search , Alpha-Beta Pruning (i)
- 5-3 Alpha-Beta Pruning (ii)
- 5-4 Asperasion Windows, NegaScout
- 5-5 Imperfect Decisions, Forward Pruning
- 5-6 Stochastic Games, Partially Observable Games
- Week 5
- Propositional Logic
- 6-1 Logical Agents (i) - Generic Knowledge-Based Agent, PEAS
- 6-2 Logical Agents (ii) - Logic, Entailment and Models
- 6-3 Propositional Logic, Inference (i) - Enumeration, Validity and Satisfiability
- 6-4 Inference (ii) - Simple Knowledge, Resolution and CNF (i) - Proof by Resolution, CNF Conversion, Resolution Algorithm
- 6-5 Resolution and CNF (ii) - Properties of Resolution, Ground Resolution Theorem
- 6-6 Resolution and CNF (iii) - Horn and Definite Clauses, Forward Chaining
- 6-7 Backward Chaining, Pros and Cons of Propositional Logic
- Week 6
- First Order Logic
- 7-1 First-Order Logic (i) - Syntax of FOL and Semantics
- 7-2 First-Order Logic (ii) - Using FOL, Inference (i) - Instantiation
- 7-3 Inference (ii) - Propositionalization, Inference (iii) - Unification
- 7-4 Inference (iii) - Unification, Inference (iv) - Forward chaining
- 7-5 Inference (iv) - Forward chaining, Inference (v) - Backward chaining
- 7-6 Logic Programing (i) - Prolog Systems
- 7-7 Logic Programing (ii) - Redundant Inference and Infinite Loops in Prolog
- 7-8 Inference (vi) - Resolution
- Week 7
- Planning
- 8-1 Planning Domain Definition Language (PDDL) (i)
- 8-2 Planning Domain Definition Language (PDDL) (ii)
- 8-3 State-Space Search, Heuristics
- 8-4 Planning Graphs
- 8-5 GRAPHPLAN
- 8-6 Course Review
- 臺大開放式課程（NTU OpenCourseWare）：計算機概論
- Week8
Summary of User Reviews
The course 'Artificial Intelligence' on Coursera received positive reviews from many users. They found the content of the course to be informative and the instructor to be knowledgeable. One key aspect that many users thought was good is the practical approach to learning AI.Pros from User Reviews
- Informative content
- Knowledgeable instructor
- Practical approach to learning AI
- Good pacing of the course
- Easy to understand explanations
Cons from User Reviews
- Lack of hands-on exercises
- Some technical issues with the platform
- Not enough depth in certain topics
- Some lectures were too long
- Limited interaction with the instructor
于天立
4.8 Raiting
人工智慧：搜尋方法與邏輯推論 (Artificial Intelligence - Search & Logic)
- 4.8
-
![]()
![]()
![]()
![]()
![]()
本課程分為人工智慧（上）、人工智慧（下）兩部份，第一部分除了人工智慧概論外，著重在目標搜尋、meta heuristic、電腦對弈、演繹學習（包含證言邏輯、一階邏輯及 planning ）等技術。這些技術主要發展時機為人工智慧的第一波及第二波熱潮，也就是 1950 年代至 1990 年代附近的主流發展，即使到現在也在各個領域廣為應用。 課程教學目標： 使同學對人工智慧有基礎概念 同學能夠理解如何運用目標搜尋技術及演繹學習方式達成人工智慧 同學能將相關技術應用到自己的問題上 Introduction 1-1 History of AI：TuringTest and Its Application, Chinese Room Argument...
