<![CDATA[
# <p class="text-h">Homework 1 - PM2.5 Prediction</p>
### <p class="text-hh">Announcements</p>
<!--#### 3/18
* 請各位修課同學務必注意，github請勿上傳dataset!!!
#### 3/15
* Strong baseline release!
* Hands-on session materials：<a href="./sample_code.html" target="_blank">sample code</a> and <a href="https://docs.google.com/presentation/d/1mY9gG-QCJ21NpjOQ--bFnoFQRhs0TlKox8AegWni518/edit?usp=sharing" target="_blank">supplementary slide</a>.
#### 3/11
* 新增hw1_best.sh套件限制：
#### 3/9
* HW1小老師表單連結已公布! 請注意表單僅統計至3/13 21:59:59(GMT+8)。-->
#### 3/6
* HW1 Virtual Environment release <a href="https://goo.gl/6HQcqH" target="_blank"><i class="fa fa-download"></i></a>
#### 3/1
* Sample code release <a href="https://github.com/ntumlta2019/hw1" target="_blank"><i class="fa fa-book"></i></a>
* Public Strong Baseline release!
#### 2/22
* 新增hw1_best.sh套件限制：
* Tensorflow == 1.12.0
* Pytorch == 1.0.1
* Keras == 2.2.4
* Scikit-learn == 0.20.2
#### 2/21
* HW1 release!
* 手把手 release!
<!--
<hr>
### <p class="text-hh">Lecture Slides</p>
* Week1(3/1/2018): Introduction <a href="https://drive.google.com/open?id=1pOFQFyzK9b1kbHnx3-LoZlgQsgBKSVDR">[pdf]</a>
* Week1(3/1/2018): Regression <a href="https://drive.google.com/open?id=1T66NyD5jEBlLfXx8TI2G-0QN4tlFrMu1">[pdf]</a>
* Week1(3/1/2018): Bias and Variance <a href="https://drive.google.com/open?id=1fQql6dwCvp4WZ9FkzchHqEWuYcGgFLDQ">[pdf]</a>
* Week2(3/8/2018): Gradient Descent <a href="https://drive.google.com/open?id=17iGC3qPP2lrCuaCbfbTx0AISZAC-WhhR">[pdf]</a>
* Week2(3/8/2018): Classification <a href="https://drive.google.com/open?id=1vooNE7ssbO_RxA7LAPoyydk3ZZVcNJbI">[pdf]</a>
* Week2(3/8/2018): Logisic Regression <a href="https://drive.google.com/open?id=1hfu3JbOn2JejkVLRPFMfShteq5YXyUX_">[pdf]</a>
-->
<hr>
### <p class="text-hh">Links</p>
* 作業投影片 <a href="https://docs.google.com/presentation/d/1gM32ovHHH6Dv4I3Ow0P3XXz1savkBp8jWSqSVp0Xwg4/edit#slide=id.g4cd6560e29_0_10/" target="_blank"><i class="fa fa-book"></i></a>
* 手把手投影片 <a href="https://docs.google.com/presentation/d/1TkPQoOPyDY9IzzuaVsYq1E26D1NTmi_QA9S9c-rw9K8/edit#slide=id.g5047f99cc6_0_0" target="_blank"><i class="fa fa-book"></i></a>
* Kaggle 連結 <a href="https://www.kaggle.com/c/ml2019spring-hw1" target="_blank"><i class="fa fa-trophy"></i></a>
* General Tutorial 投影片 <a href="https://goo.gl/Tvsy1i" target="_blank"><i class="fa fa-book"></i></a>
* Github Repo 表單 <a href="https://docs.google.com/forms/d/e/1FAIpQLSf_BL_NZJVVL-xzsDXBVQtTShpwih07SbgRmQrYhmzrZHx7yQ/viewform" target="_blank"><i class="fa fa-pencil-square-o"></i></a>
* Report 模板 <a href="https://docs.google.com/document/d/1n9GeHikNOUeckA6WV-gDASSg_gqzgvoqQMZX0QJv1xc/edit" target="_blank"><i class="fa fa-file-text"></i></a>
* 遲交表單 <a href="https://docs.google.com/forms/d/1Ui_-NaLggaOtHYtcH4Zymz7ZtOT_n8IeWDP6rv78FHA/viewform?edit_requested=true" target="_blank"><i class="fa fa-pencil-square-o"></i></a>
* Facebook Group <a href="https://www.facebook.com/groups/314613059175222/" target="_blank"><i class="fa fa-facebook-square"></i></a>
<!--* 小老師表單 <a href="https://goo.gl/feHp6o" target="_blank"><i class="fa fa-pencil-square-o"></i></a>-->
<hr>
### <p class="text-hh">Deadlines</p>
* Simple Bonus Deadline: 02/28/2019 23:59:59 (GMT+8)
* Kaggle Deadline: 03/07/2019 11:59:59 (GMT+8)
* Github Deadline: 03/08/2019 23:59:59 (GMT+8)
<hr>
### <p class="text-hh">Assignment Regulation</p>
* ALL code must be written in python3.6
* For `hw1.sh` :
* ALL python standard library is permitted (e.g. sys, csv, time)
* numpy >= 1.14
* scipy == 1.2.1
* pandas == 0.24.1
* For `hw1_best.sh` :
* Meet the higher score you choose in kaggle
* ALL toolkit is permitted (however with some version limitation)
* Tensorflow == 1.12.0
* Pytorch == 1.0.1
* Keras == 2.2.4
* Scikit-learn == 0.20.2
<hr>
### <p class="text-hh">FAQ</p>
<p>Q1：請問kaggle的組隊人數上限？</p>
<p>A1：hw1為個人作業，不用在kaggle上進行組隊。</p>
<p>Q2: 如果只有實作 gradient descent，hw1.sh跟hw1_best.sh可以繳交同一份script嗎？</p>
<p>A2: 可以的。</p>
<p>Q3: 請問report第一題到底要我們比較哪兩個模型？</p>
<p>A3：簡單來說是比較以下兩種模型：</p>
<ul>
<li>9x18+1=163種feature（9小時內所有18種測量值+bias項）</li>
<li>9x1+1=10種feature（9小時內所有PM2.5值+bias項）</li>
</ul>
<p>Q4：所以hw1_best.sh可能會用到的套件也要寫信跟助教確認嗎？</p>
<p>A4：不用！只有hw1.sh中若會使用到numpy, scipy, pandas以外的套件才需要寫信。</p>
<p>Q5：hw1.sh 可以 import sys 嗎？</p>
<p>A5：sys 屬於 python standard library，所以是可以使用的。其他可以使用的內建套間可以參照：<a href="https://docs.python.org/3/library/index.html">python standard library</a>。</p>
<hr>
]]>