114年第2學期-5569 智慧計算 課程資訊

評分方式

評分項目	配分比例	說明
出席	10
平時作業	15
期中報告	35
期末專題實作與報告	40

教育目標

This course integrates meta-heuristics and reinforcement learning to provide comprehensive training in intelligent decision-making systems. The first part focuses on meta-heuristic algorithms for combinatorial optimization, including genetic algorithms, simulated annealing, tabu search, and swarm intelligence. The second part introduces reinforcement learning fundamentals, covering Markov decision processes, Q-learning, policy gradient methods, and deep reinforcement learning. Emphasis is placed on both theoretical understanding and practical implementation. Students will develop algorithms to solve real-world problems in their research domains, learning to select appropriate methods, tune parameters, and evaluate performance effectively.

基本資料

選修課，學分數：0-3
上課時間：五/2,3,4[E230]
修課班級：工工碩博1,2
修課年級：1年級以上
選課備註：IP7103

參考書目

Walpole, R.E., Myers, R.H., Myers, S. L. and Ye, Keying (2016). Probability and
Statistics For Engineers and Scientists. (Global 9th edition). Pearson Education.

Ross, S. M. (2018). Introduction to Probability and Statistics (5th edition).
Elsevier Academic Press.