added first draft notebooks for similarity section

course/attention/03_bidirectional_attention.ipynb

@@ -6,10 +6,17 @@
    "source": [
     "# Bi-directional Attention\n",
     "\n",
-    "We've explored both dot-product attention, and self-attention. Where dot-product compared two sequences, and causal attention compared previous tokens from the *same sequence*, bidirectional attention compares tokens from the *same sequence* in both directions, subsequent and previous. This is as simple as performing the exact same operation that we performed for *self-attention*, but excluding the masking operation - allowing each word to be mapped to every other word in the same sequence. So, we could call this *bi-directional **self** attention*. This is particularly useful for masked language modeling - and is used in BERT (**Bidirectional Encoder** Representations from Transformers) - bidirectional self-attention refers to the *bidirectional encoder*, or the *BE* of BERT.\n",
+    "We've explored both dot-product attention, and self-attention. Where dot-product compared two sequences, and self attention compared previous tokens from the *same sequence*, bidirectional attention compares tokens from the *same sequence* in both directions, subsequent and previous. This is as simple as performing the exact same operation that we performed for *self-attention*, but excluding the masking operation - allowing each word to be mapped to every other word in the same sequence. So, we could call this *bi-directional **self** attention*. This is particularly useful for masked language modeling - and is used in BERT (**Bidirectional Encoder** Representations from Transformers) - bidirectional self-attention refers to the *bidirectional encoder*, or the *BE* of BERT.\n",
     "\n",
     "![Bidirectional Attention](../../assets/images/bidirectional_attention.png)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

course/introduction/02_transformer_heads.ipynb

@@ -38,6 +38,13 @@
     "\n",
     "![Q&A BERT showing additional start/end token classifiers](../../assets/images/qa_linear_bert.png)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

course/similarity/00_intro.ipynb

@@ -0,0 +1,32 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ML",
+   "language": "python",
+   "name": "ml"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}