Fix typos in documentation (#758)

Fix typos in documentation

[ reviewed by @ankona ]
[ committed by @jsta ]

Author: jsta

doc/changelog.md

@@ -15,6 +15,7 @@ Description
 
 - Implement workaround for Tensorflow that allows RedisAI to build with GCC-14
 - Add instructions for installing SmartSim on PML's Scylla
+- Fix typos in documentation
 
 Detailed Notes
 
@@ -30,6 +31,7 @@ Detailed Notes
   have yet to be installed at a system-wide level. Scylla has
   its own entry in the documentation.
   ([SmartSim-PR733](https://github.com/CrayLabs/SmartSim/pull/733))
+- Fix typos in the `train_surrogate` tutorial documentation
 
 
 ### 0.8.0

doc/tutorials/ml_training/surrogate/README.md

@@ -3,6 +3,6 @@
 
 In this example, a neural network is trained to act like a surrogate model and to solve a
 well-known physical problem, i.e. computing the steady state of heat diffusion. The training
-dataset is constructed by running simualations *while* the model is being trained.
+dataset is constructed by running simulations *while* the model is being trained.
 
-The notebook also displays how the surrogate model prediction improves during training.
+The notebook also displays how the surrogate model prediction improves during training.

doc/tutorials/ml_training/surrogate/train_surrogate.ipynb

@@ -15,7 +15,7 @@
     "\n",
     "In this notebook, a neural network is trained to act like a surrogate model and to solve a\n",
     "well-known physical problem, i.e. computing the steady state of heat diffusion. The training\n",
-    "dataset is constructed by running simualations *while* the model is being trained.\n",
+    "dataset is constructed by running simulations *while* the model is being trained.\n",
     "\n",
     "## 2D Heat Diffusion and Steady State\n",
     "Throughout this notebook, the heat equation will be solved on the two-dimensional domain $[0,1]\\times[0,1]$, setting the initial temperature to 0 K, except\n",