開課單位： 國立臺北大學
| 編號 | 課程名稱 | 學分數 | 授課教師 | 課程概述 |
| 1 | 多媒體訊號處理 | 3 | 江振宇 | 1.了解數位訊號處理之實際應用 2.研習資料之表示方法及通訊方法 3.數位文字、圖像、影像及聲音之表示及處理 4.以程式語言實作基礎多媒體訊號處理系統 |
| 2 | 通訊原理 | 2 | 陳建宏 | From this course, students learn the fundamental communication systems including analog communication systems in early days and basic idea of modern digital communication systems |
| 3 | 網路安全與深度學習 | 3 | 曾俊元 | 1.網路安全結合深度學習之理論介紹 2.網路安全資料集基於深度學習分析實作 3.最新論文研讀與報告 4.網路CTF實作 |
| 4 | 影像處理導論 | 3 | 林道通 | 學習數位影像的基本形式，以及我們如何藉著電腦對一個影像進行處理，使得影像中的資訊能夠更清晰的呈現出來。這一門課有需要寫程式的作業，同學可以用C++, Matlab, Octave 或 Python來做作業。 |
| 5 | 電腦視覺 | 3 | 林道通 | This course provides necessary theory and example for students and practitioners who will work in fields where significant information must be extracted automatically from images. Our goals were to provide a basic set of fundamental concepts and algorithms and also discuss some of the exciting evolving application areas. |
| 6 | 人工神經網路與深度學習 | 3 | 林道通 | The objectives of this course are to study the basic neural networks architecture and theory, explore the recent development of deep learning, and extend to their advanced applications. The students are to be exposed to a broad range of domain-specific applications study and analysis, and state-of-art research in neural networks and deep learning. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of the state-of-the-art visual recognition systems. This course is a deep dive into details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 18-week course, students will learn to implement, train and debug their own neural networks. We will focus on teaching how to set up the problem of image recognition, the learning algorithms (e.g. backpropagation), practical engineering tricks for training and fine-tuning the networks and guide the students through hands-on assignments and a final course project. |
| 7 | 數位通訊系統模擬 | 3 | 李忠益 | 本課程之目的是以SystemView軟體或SystemVue軟體模擬方式強化同學對通訊系統(原理)之了解並培養分析與設計之能力。讓學生能夠學習且充分理解通訊系統之傳輸通道、訊號與系統、振幅與頻率調變/解調、雜訊、振幅與頻率解調效能、超外差式接收機、取樣定理以及PAM/PPM/PWM脈碼調變。 |
| 8 | 光通訊 | 3 | 李忠益 | 本課程為當今光通訊系統之基本介紹。在本課程中，學生將學習：基本的光纖概念、光纖元件的應用以及光通訊系統的了解，包含光纖通訊、分波多工(WDM)系統、光通訊調變模式、光纖/微波通訊(Radio over Fiber)系統、可見光通訊、自由空間光通訊、水下光通訊與光學網路等。本課程將強調光通訊系統在於實體層面的設計概念，部分基本而關鍵的光學網路協定也將涵蓋於其中。本課程適合有興趣於通訊及光電領域的大四與研究所同學，對於光通訊系統與元件的物理層面進行更深入的探討與研究。 |
| 9 | 機器學習導論 | 3 | 吳信龍 | 本課程為導論課程，著重介紹機器學習，其中更聚焦於深度學習也包含近年來的新技術，目標讓同學能透過演練能了解與實作深度學習技術。 |
| 10 | 無線網路導論 | 3 | 陳裕賢 | 介紹目前現有的所有無線網路技術。 |
| 11 | 控制系統設計與模擬 | 3 | 楊棧雲 | The course has been refined to adapt the emerging technical changes. The course is aimed to pave a way for the students who want to know how to design a controller to manipulate and control a system. This kind of tasks are currently very popular for robotics, automation and home appliances. With the particular inspirations from newly developed techniques, this kind of design patterns would also potentially benefit to environmental controls, sustainable energy topics, industry 4.0, intelligent medical applications, assistive techniques and precision agriculture in turn. In this course, we emphasize a practical implementation of the controllers. Two parts of topics will be embedded into the course, including those related to microcontroller, and those to control system. Most of topics will be introduced with practically implementation with Matlab. Finally, with a competition of self-initiated final projects from the students, the students could be innovated through the works invented by his colleagues. |
| 12 | 智慧型控制 | 3 | 楊棧雲 | This course is designed mainly for students to study the AI adaptive systems, some aspects regarding control are also included. The major technique comes through the whole course will be the reinforcement learning which is promisingly an emerging technique for this kind of applications. After a short review of the control systems, the course is started with an overall introduction of reinforcement learning, including the basic Hidden Markov model and Markov decision process. The elementary model-based and model-free schemes will then be followed up. The skills in manipulating the system including value function approximation, policy gradient, integrating learning and planning, and exploration and exploitation are also scheduled in the course. In the course, some of the crucial properties of reinforcement accommodating with the control theory will be conducted to bring the system to the control applications. Many kinds of important principles for controller design will be addressed with their tendency inspired by AI. |
| 13 | 訊號與系統 | 3 | 謝欣霖 | To learn fundamentals of signal and system analysis, with applications drawn from filtering, multimedia processing, and communications. |
|
|
|
臺北大學教務處課務組電話：(02)8674-1111(分機66110~66117)/ course@gm.ntpu.edu.tw |