ABLkit/examples/hed/hed.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Handwritten Equation Decipherment (HED)\n",
    "\n",
    "This notebook shows an implementation of [Handwritten Equation Decipherment](https://proceedings.neurips.cc/paper_files/paper/2019/file/9c19a2aa1d84e04b0bd4bc888792bd1e-Paper.pdf). As shown below, the handwritten equations consist of sequential pictures of characters. The equations are generated with unknown operation rules from images of symbols ('0', '1', '+' and '='), and each equation is associated with a label indicating whether the equation is correct (i.e., positive) or not (i.e., negative). An agent is required to learn from a training set of such equations and then to predict labels of unseen equations. Note that the operation rules governing the label assignment of labels, \"xnor\" in this example, are unknown, and the sizes of equations can be different."
   ]
  },
  {
   "attachments": {
    "image.png": {