<![CDATA[
# <p class="text-h">Homework 7 - Unsupervised Learning</p>
### <p class="text-hh">Announcements</p>
#### 5/16
* Strong baseline release
#### 5/14
* slides page 12 update.
#### 5/11
* slides page 10 update.
#### 5/9
* Report template link & data link update !
* HW7 release!
<hr>
### <p class="text-hh">Links</p>
* 作業投影片 <a href="https://docs.google.com/presentation/d/1A_o2m6_bMFtOur660ZpBT162kB5B8DI_iHQaWYUMMQc/edit?usp=sharing" target="_blank"><i class="fa fa-book"></i></a>
* Kaggle 連結 <a href="https://www.kaggle.com/c/ml2019spring-hw7/" target="_blank"><i class="fa fa-trophy"></i></a>
* Report 模板 <a href="https://docs.google.com/document/d/1EkFVGq8g5DIMLD0IMnx8wqF_gGyQjH5INw181JpMDHg/edit?usp=sharing" target="_blank"><i class="fa fa-file-text"></i></a>
* 遲交表單 <a href="https://forms.gle/baGVu9taYirMtchN8" target="_blank"><i class="fa fa-pencil-square-o"></i></a>
* Sample code (PCA of colored faces)<a href="https://hackmd.io/nBZQRocKSe204LRdlO5XUQ" target="_blank"><i class="fa fa-book"></i></a>
* Sample code (image clustering)<a href="https://hackmd.io/9tpCZvCdTGKH2aUwspSSlQ?view" target="_blank"><i class="fa fa-book"></i></a>
* Facebook Discussion <a href="https://www.facebook.com/notes/machine-learning2019-spring/hw7-%E8%A8%8E%E8%AB%96%E5%8D%80/357253908244470/" 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: 05/16/2019 11:59:59 (GMT+8)
* Kaggle Deadline: 05/23/2019 11:59:59 (GMT+8)
* Github Deadline: 05/24/2019 23:59:59 (GMT+8)
<hr>
### <p class="text-hh">Assignment Regulation</p>
* ALL code must be written in python3.6
* For `pca.sh` :
* ALL python standard library is permitted (e.g. sys, csv, time)
* numpy >=1.14
* scikit-image == 1.15.0
* For `cluster.sh` :
* ALL python standard library is permitted (e.g. sys, csv, time)
* Keras == 2.2.4
* Tensorflow == 1.12.0
* pytorch == 1.0.1
* Numpy >= 1.14
* Pandas >= 0.20
* scipy == 1.2.1
* scikit-image == 0.15.0
* pillow == 6.0.0
* scikit-learn == 0.20.3
* Multicore-TSNE == 0.1
<hr>
### <p class="text-hh">FAQ</p>
<p>Q1：請問kaggle的組隊人數上限？</p>
<p>A1：hw7為個人作業，不用在kaggle上進行組隊。</p>
<p>Q2：reproduce 規則？</p>
<p>A2：</p>
1. reproduce時間限制10分鐘不包含下載model時間
<br>2. reproduce標準為kaggle勾選的二擇一即可
<br>3. baseline分數以kaggle為準
<br>4. reproduce誤差為±0.2%
<br>
<p>Q3: 關於cluster.sh的規定?</p>
<p>A3: kaggle的上傳必須以autoencoder實作降維，也就是說你的model要含有autoencoder的結構，但還是可以搭配其他的降維方法如PCA, SVD, t-SNE一起使用。</p>
<hr>
]]>