論文研討
Seminars
學期
111-2
學分
0
學分
當期課號
535450
永久課號
EEAI30001
開課單位
人工智慧技術與應用碩士學位學程
授課教師
廖元甫、黃紹華
校區
光復
類別
必修
上課時間表
| 節 | 週三 |
|---|---|
5 13:20–14:10 | 論文研討 ED301 2 節連堂 |
6 14:20–15:10 |
* 根據陽明交大上課時間表所列
概述
本課程將課堂演講。邀請各領域專業人士從事專題演講,引導學生在相關研究領域中產生更寬廣的創意與想法。
先修科目
限人工智慧技術與應用碩士學位學程學生修習。
教學方式
課堂演講方式進行。若有特殊情況(如疫情)則搭配線上演講或補充影片 1.課程介紹 *1 2.專家/名人Youtube觀賞(張忠謀、蔡力行、吳嘉隆、謝金河、楊瑞臨、魏哲家、明居正、李開復、...)*4 3.專家/名人實體演講*6(AI, IoT, 5G, FVV, 智慧醫療, ...) 4.專家/名人線上演講*3
評分方式
1. 出席率,並且每次演講須交一份個人演講心得100% 3. 演講中問問題,可加分
週次計畫
| 週次 | 主題 |
|---|---|
| 第 1 週 | 廖元甫教授/黃紹華教授 課程簡介 |
| 第 2 週 | 從傳統電信到AIoT,黃紹華 |
| 第 3 週 | 王崇喆,國立清華大學.資訊工程學系.多媒體資訊檢索實驗室.博士 Kaggle競賽甘苦談: 2022/06,餘光能源太陽能發電量預測比賽,一百七十九個隊伍中,Public LB 第五名,Private LB 第十名 2022/01,玉山銀行信用卡消費類別推薦比賽,三百多個隊伍中第九名 2021/07,Tomofun 狗音辨識比賽,一百多個隊伍中第九名(團隊競賽) |
| 第 4 週 | 專家/名人Youtube影片觀賞-1 |
| 第 5 週 | 顏安孜An-Zi Yen - 國立陽明交通大學資訊工程學系助理教授 自然語言處理、資訊檢索與擷取、深度學習、人工智慧 http://nlg.csie.ntu.edu.tw/~azyen/ |
| 第 6 週 | 專家/名人Youtube影片觀賞-2 |
| 第 7 週 | 陳碩漢 https://shuohanchen.com/ |
| 第 8 週 | 期中考週,暫停一次 |
| 第 9 週 | 陳志成:聯發科 Title: 人工智慧與IC設計 - 下一代智慧裝置的發展趨勢 (AI and IC Design - The Trend of Next Generation Smart Devices) |
| 第 10 週 | Peter Wolf 卓騰語言科技: https://www.droidtown.co/zh-tw/ |
| 第 11 週 | 林緯 Wei Lin 群聯電子股份有限公司,創新技術研發事業群-研發一處副處長 https://www.phison.com/ |
| 第 12 週 | 聯發科技術副總張宏銘 與電信所電波組一起上課EDB26 |
| 第 13 週 | 李錦輝,美國喬治亞理工教授 Title: From Classical Universal Approximation to Deep Regression in Machine Learning Recently there arise plenty of algorithms supporting artificial intelligence (AI) based applications. However, most of them are simply reporting experimental results without theoretical analyses. In this talk, we attempt to interpret deep regression, a new approach to solving classical signal processing problems leveraging upon machine learning and big data paradigms. Based on Komogorov’s Representation Theorem (1957), a multivariate scalar function can be expressed exactly as a superposition of a finite number of outer functions with another linear combination of inner functions embedded within. Cybenko (1989) developed a universal approximation theorem showing such a scalar function can be approximated by a superposition of sigmoid functions, inspiring a new wave of neural network algorithms. Barron (1993) later proved that the error in approximation can be tightly bounded and related to the representation power in learning theory. In order to make the mapping learnable and computable for some practical applications, we cast the classical function approximation problems into a nonlinear regression setting using deep neural networks (DNNs) as mapping functions, such that the DNN parameters can be estimated with deep learning and big data configurations for machine learning. In this talk, we first develop four new theorems to generalize the universal approximation theorems from sigmoid to DNNs and from vector-to-scalar to vector-to-vector regression. We also show that the generalization loss or regression error in machine learning can be decomposed into three terms, approximation, estimation and optimization errors, such that each of them can be tightly bounded, separately. Many classical speech processing problems, such as enhancement, source separation and dereverberation, can be formulated as finding mapping functions to transform input to output spectra. Our developed theorems also provide some guidelines for parameter and architecture selections in DNN designs. In a series of experiments for high-dimensional nonlinear regression, we validate our theory in terms of representation and generalization powers in machine learning for speech spectrum mapping. As a result, DNN-transformed speech usually exhibits a good quality and a clear intelligibility under adverse acoustic conditions. Finally, our proposed deep regression framework was also tested on recent challenging tasks in CHiME-2, CHiME-4, CHiME-5, CHiME-6, REVERB and DIHARD III. Based on the top quality achieved in microphone-array based enhancement, separation and dereverberation, our teams scored the lowest error rates in almost all the above-mentioned open evaluation scenarios. Speaker: Chin-Hui Lee, School of ECE, Georgia Tech Chin-Hui Lee is a professor at School of Electrical and Computer Engineering, Georgia Institute of Technology. Before joining academia in 2001, he had accumulated 20 years of industrial experience ending in Bell Laboratories, Murray Hill, as the Director of the Dialogue Systems Research Department. Dr. Lee is a Fellow of the IEEE and a Fellow of ISCA. He has published over 550 papers and 30 patents, with more than 55,000 citations and an h-index of 80 on Google Scholar. He received numerous awards, including the Bell Labs President's Gold Award in 1998. He won the SPS's 2006 Technical Achievement Award for “Exceptional Contributions to the Field of Automatic Speech Recognition''. In 2012 he gave an ICASSP plenary talk on the future of automatic speech recognition. In the same year he was awarded the ISCA Medal in Scientific Achievement for “pioneering and seminal contributions to the principles and practice of automatic speech and speaker recognition''. His two pioneering papers on deep regression accumulated over 2000 citations and won a Best Paper Award from IEEE Signal Processing Society in 2019. |
| 第 14 週 | 漢民科技劉順吉副總 |
| 第 15 週 | 鄭琬蓉小姐 清大性平業務承辦人。 |
| 第 16 週 | 期末考週,暫停一次 |
| 第 17 週 | |
| 第 18 週 |
教科書
無
Office Hours
- 地點
- ED705
- 時間
- (三)14:00~16:00
- 聯絡方式
- hsf@nctu.edu.tw