Tweak PySR demo

examples/pysr_demo.ipynb

@@ -990,6 +990,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "3hS2kTAbbDhL"
@@ -999,9 +1000,9 @@
         "\n",
         "Let's consider a time series problem:\n",
         "\n",
-        "$$ z = y^2,\\quad y = \\frac{1}{100} \\sum(y_i),\\quad y_i = x_{i0}^2 + 6 \\cos(2*x_{i2})$$\n",
+        "$$ z = y^2,\\quad y = \\frac{1}{10} \\sum(y_i),\\quad y_i = x_{i0}^2 + 6 \\cos(2*x_{i2})$$\n",
         "\n",
-        "Imagine our time series is 100 timesteps. That is very hard for symbolic regression, even if we impose the inductive bias of $$z=f(\\sum g(x_i))$$ - it is the square of the number of possible equations!\n",
+        "Imagine our time series is 10 timesteps. That is very hard for symbolic regression, even if we impose the inductive bias of $$z=f(\\sum g(x_i))$$ - it is the square of the number of possible equations!\n",
         "\n",
         "But, as in our paper, **we can break this problem down into parts with a neural network. Then approximate the neural network with the symbolic regression!**\n",
         "\n",
@@ -1018,7 +1019,7 @@
       "source": [
         "###### np.random.seed(0)\n",
         "N = 100000\n",
-        "Nt = 100\n",
+        "Nt = 10\n",
         "X = 6 * np.random.rand(N, Nt, 5) - 3\n",
         "y_i = X[..., 0] ** 2 + 6 * np.cos(2 * X[..., 2])\n",
         "y = np.sum(y_i, axis=1) / y_i.shape[1]\n",
@@ -1299,14 +1300,15 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6WuaeqyqbDhe"
       },
       "source": [
         "Recall we are searching for $y_i$ above:\n",
         "\n",
-        "$$ z = y^2,\\quad y = \\frac{1}{100} \\sum(y_i),\\quad y_i = x_{i0}^2 + 6 \\cos(2 x_{i2})$$"
+        "$$ z = y^2,\\quad y = \\frac{1}{10} \\sum(y_i),\\quad y_i = x_{i0}^2 + 6 \\cos(2 x_{i2})$$"
       ]
     },
     {
@@ -1373,11 +1375,13 @@
     },
     "gpuClass": "standard",
     "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
+      "display_name": "Python (main_ipynb)",
+      "language": "python",
+      "name": "main_ipynb"
     },
     "language_info": {
-      "name": "python"
+      "name": "python",
+      "version": "3.10.9"
     }
   },
   "nbformat": 4,