training vi and normalizing flows wip\

trainings/variational_inference_core_team/vae.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Variational Autoencoders\n",
+    "\n",
+    "A Bayesian approach\n",
+    "\n",
+    "\n",
+    "## Suddenly a wild fashion-set appears...\n",
+    "<img src=\"img/fashion-mnist-sprite.png\"/>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generative model\n",
+    "\n",
+    "<img src=\"./img/plate-vae.png\"/>\n",
+    "\n",
+    "For each image $x_i$:\n",
+    "\n",
+    "$$\\begin{eqnarray}\n",
+    "z_i &\\sim& P(z) \\\\\n",
+    "x_i &\\sim& P(x|z_i)\n",
+    "\\end{eqnarray}$$\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Bayesian inference\n",
+    "\n",
+    "$$P(z|x) = \\frac{P(x|z)P(z)}{P(x)} $$\n",
+    "\n",
+    "## Can we solve this with MCMC?\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Approximate distribution\n",
+    "\n",
+    "Let's define an approximate distribution $Q(Z) \\approx P(z|x)$. We optimize the variables of $Q(z)$ so that it will be 'closer' to the true posterior $P(z|x)$\n",
+    "\n",
+    "<img src=\"./img/easydist.png\"/>\n",
+    "\n",
+    "<img src=\"./img/dafuq.jpg\"/>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## KL-divergence\n",
+    "There is a reason we choose to measure the 'closeseness' with the KL-divergence and not a real distance metric, such as the Wasserstein distance."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}