智慧系統實驗室 INTELLIGENT SYSTEM LAB.

Artificial Intelligence

【Handout: AI Concept| Proposition | First-order Logic | Genetic Algorithm |Ant Algorithm |Probability table| Hypothesis Testing| ANOVA| T-test | Simple Regression | Logistic Regression | Naive Bayes Classifier| KMeans | KNN |Association Rules| Decision Tree | Random Forest | Support Vector Machine | Reinforcement Learning | Neural Networks | Deep Neural Network| Convolutional Neural Networks | Long Short-Term Memory | Generative Adversarial Networks| Large Language Model | Retrieval-Augmented Generation | Ensemble Learning】
  1. Objective: To introduce artificial intelligence algorithms and application technologies. Students taking this course will have a basic knowledge of AI and be able to engage in related practice experiments. The content includes Predicate and Proposition, Theory Proving, Genetic Algorithm, T-test, Logistic Regression, Naive Bayes Classifier, KMeans, KNN, Decision Tree, Random Forest, Support Vector Machine, Reinforcement Learning, Deep Neural Networks, Convolutional Neural Networks, Long Short-Term Memory, Large Language Model, Retrieval-Augmented Generation, and Ensemble Learning.
  2. Textbook: Self-developed teaching materials, research papers.
  3. Place/Time: Wednesday 13:10~16:00, Technology Research Building 1223. TA office hours: Wednesday 18:10~20:00, Research Building 1223.
  4. Instructor: Dr. Jong-Yih, jykuo@ntut.edu.tw, TA: (@ntut.edu.tw)
  5. Scopes: Artificial Intelligence Concept: Predicate and Proposition, Theory Proving; Optimization Concept: Genetic Algorithm, Ant Algorithm; Statistical Inference: Hypothesis Testing, T-test, Logistic Regression, Naive Bayes Classifier; Machine Learning Clustering: K-Means; Machine Learning Classification: KNN, Decision Tree, Random Forest, Support Vector Machine; Reinforcement Learning: Q-Learning; Deep Learning: Deep Neural Networks, Convolutional Neural Networks, Long Short-Term Memory; Large Language Model, Retrieval-Augmented Generation, Ensemble Learning.
  6. Prerequisite knowledge: Familiar with Python programming
  7. Exam and Grading
    Class Practices and Assignments 30%
    Quiz 30%
    Projects (Personal and Teams) 40%
  8. Schedules
    Week01(02/19): AI Concept, Proposition
    Week02(02/26): First-order Logic and Theory Proving
    Week03(03/05): Genetic Algorithm, Ant Algorithm
    Week04(03/12): Hypothesis Testing
    Week05(03/19): Sports Day
    Week06(03/26): ANOVA and T-test
    Week07(04/02): Logistic Regression, Naive Bayes Classifier
    Week08(04/09): Quiz 1
    Week09(04/16): K-Means, KNN, Association Rules
    Week10(04/23): Decision Tree, Random Forest
    Week11(04/30): Support Vector Machine, Reinforcement Learning,
    Week12(05/07): Neural Networks, Deep Neural Networks
    Week13(05/14): Convolutional Neural Networks
    Week14(05/21): Long Short-Term Memory, Generative Adversarial Networks
    Week15(05/28): Large Language Model, Retrieval-Augmented Generation, Ensemble Learning
    Week16(06/04): Quiz 2
    Week17(06/11): Term Project: Final Report, Demo
    Week18(06/18): Term Project: Final Report, Demo
回頁首