論文研討
Colloquium
學期
111-2
學分
0
學分
當期課號
536717
永久課號
SCMA30045
開課單位
應用數學系
授課教師
李育杰
校區
光復
類別
必修
上課時間表
| 節 | 週二 |
|---|---|
5 13:20–14:10 | 論文研討 SA223 2 節連堂 |
6 14:20–15:10 |
* 根據陽明交大上課時間表所列
概述
本課程邀請學者教授以演講方式進行,希望同學能了解數學在諸多領域的應用,並期盼同學能多與講者互動,達到更好的學習效果。
先修科目
具備基礎數學知識
教學方式
須從整學期演講課程中,繳交至少三份紙本心得報告,不已三份為限。
評分方式
出席率: 70%, 心得報告: 20% 課堂提問: 10%
週次計畫
| 週次 | 主題 |
|---|---|
| 第 1 週 | 準備週,No lecture |
| 第 2 週 | Title: Unrolling Parsimonious Features for A Novel Boosting Strategy in Financial Trading Abstract: Deriving informative features from noisy signals delivered by the markets is consequential to applying machine learning in trading tasks. Using technical indicators introduced by financial engineering or signal processing as the features fail to fit into the target task data due to their deterministic calculating methods. Learning feature descriptors from data may dictate relevant features, but the noise within the fetched signals can misguide the learning procedure and thus hinder the application's performance. To solve this problem, we proposed to obtain the features using the parsimonious representations of input signals, which were proven promising regarding de-noising images and audio. Deriving such representations is formulated as the convolutional sparse coding (CSC) with the L0 regularization function. Then, we unroll a non-convex, non-smooth proximal splitting algorithm that solves the CSC to construct a recurrent neural network as the feature descriptor. In addition, we proposed a novel boosting method named profit boost that ensembles multiple machine learning models to enhance the performances of trading tasks further. We also proposed a general learning framework that allows our feature descriptor and boosting method to consider numerous input signals from different sources. The experimental results demonstrate that the trading strategy provided by the proposed methods significantly outperforms the prior ones derived using machine learning regarding trading profits and stability. Biography: Guan-Ju Peng is currently an associate professor in the department of applied mathematics at National Chung Hsing University. His research interests focus on designing machine learning priors and developing their optimization algorithms in image processing, natural language processing, and financial technology. |
| 第 3 週 | 紀念日 |
| 第 4 週 | 香港大學 劉宏宇教授 |
| 第 5 週 | |
| 第 6 週 | |
| 第 7 週 | |
| 第 8 週 | |
| 第 9 週 | |
| 第 10 週 | |
| 第 11 週 | |
| 第 12 週 | |
| 第 13 週 | 心理諮商 |
| 第 14 週 | Host by Prof. Yi-Hsuan Lin |
| 第 15 週 | |
| 第 16 週 | |
| 第 17 週 | |
| 第 18 週 |
教科書
無
Office Hours
- 時間
- Please contact me by e-mail: yuhjye@math.nctu.edu.tw
- 聯絡方式
- yuhjye@math.ntcu.edu.tw