more

Author: mli

units/attention.md

@@ -13,3 +13,14 @@
     [HTML](https://nbviewer.jupyter.org/url/courses.d2l.ai/berkeley-stat-157/slides/4_25/seq2seq-attention.ipynb)
   - Transformer [Jupyter](../../slides/4_25/transformer.ipynb),
     [HTML](https://nbviewer.jupyter.org/url/courses.d2l.ai/berkeley-stat-157/slides/4_25/transformer.ipynb)
+
+
+## Videos
+
+
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/SYIdimxpj6M" frameborder="0" allowfullscreen></iframe></center>
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/SVjCIYY3Y5s" frameborder="0" allowfullscreen></iframe></center>
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/NBVjgRJZLcU" frameborder="0" allowfullscreen></iframe></center>
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/1pO-rbbLhyM" frameborder="0" allowfullscreen></iframe></center>
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/HsYPiKDTikg" frameborder="0" allowfullscreen></iframe></center>
+<center><iframe width="560" height="441" src="https://www.youtube.com/embed/9-Om2YcHhIA" frameborder="0" allowfullscreen></iframe></center>

units/index.md

@@ -27,4 +27,6 @@
    word2vec
    seq2seq
    attention
+   optimization
+   adam
 ```

units/optimization.md

@@ -8,6 +8,8 @@
 
 * Notebooks
   - [Jupyter](../../slides/4_30/gd-sgd.ipynb)
+    [HTML](https://nbviewer.jupyter.org/url/courses.d2l.ai/berkeley-stat-157/slides/4_30/gd-sgd.ipynb)
   - [Jupyter](../../slides/4_30/minibatch-sgd.ipynb)
+    [HTML](https://nbviewer.jupyter.org/url/courses.d2l.ai/berkeley-stat-157/slides/4_30/minibatch-sgd.ipynb)
 
 ## Videos