Fix typos and update instructions

Author: cr-xu

README.md

@@ -21,7 +21,7 @@ To check if you have it installed, open your terminal and type:
 git --version
 ```
 
-#### Git installation in MacOS
+#### Git installation in macOS
 
 ``` bash
 brew update

config.py

@@ -9,7 +9,6 @@
 import matplotlib
 import matplotlib.pyplot as plt
 import numpy as np
-import seaborn as sns
 import torch
 from botorch.acquisition import (
     ExpectedImprovement,

tutorial.ipynb

@@ -69,16 +69,16 @@
     "Once you have Git installed open your terminal, go to your desired directory, and type:\n",
     "\n",
     "``` bash\n",
-    "git clone https://github.com/machine-learning-tutorial/neural-networks\n",
-    "cd neural-networks\n",
+    "git clone https://github.com/machine-learning-tutorial/bayesian-optimization\n",
+    "cd bayesian-optimization\n",
     "```\n",
     "\n",
     "Or get the repository with direct download:\n",
     "\n",
     "``` bash\n",
-    "wget https://github.com/machine-learning-tutorial/neural_networks/archive/refs/heads/main.zip\n",
+    "wget https://github.com/machine-learning-tutorial/bayesian-optimization/archive/refs/heads/main.zip\n",
     "unzip main.zip\n",
-    "cd neural-networks\n",
+    "cd bayesian-optimization\n",
     "```"
    ]
   },
@@ -102,14 +102,14 @@
     "Then run the following commands:\n",
     "\n",
     "```bash\n",
-    "conda create -n nn-tutorial python=3.10\n",
-    "conda activate nn-tutorial\n",
+    "conda create -n bo-tutorial python=3.10\n",
+    "conda activate bo-tutorial\n",
     "pip install -r requirements.txt\n",
     "jupyter contrib nbextension install --user\n",
     "jupyter nbextension enable varInspector/main\n",
     "```\n",
     "\n",
-    "- After the tutorial you can remove your environment with `conda remove -n nn-tutorial --all`"
+    "- **After** the tutorial you can remove your environment with `conda remove -n bo-tutorial --all`"
    ]
   },
   {
@@ -132,7 +132,7 @@
     "Alternatively, you can create the virtual env with `venv` in the standard library\n",
     "\n",
     "```bash\n",
-    "python -m venv nn-tutorial\n",
+    "python -m venv bo-tutorial\n",
     "```\n",
     "\n",
     "and activate the env with $ source <venv>/bin/activate (bash) or C:> <venv>/Scripts/activate.bat (Windows)\n",
@@ -181,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "e538eebc",
    "metadata": {
     "slideshow": {
@@ -665,7 +665,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "52408173",
    "metadata": {
@@ -830,6 +829,7 @@
    "execution_count": null,
    "id": "e12804c8",
    "metadata": {
+    "scrolled": true,
     "slideshow": {
      "slide_type": "slide"
     }
@@ -1012,16 +1012,17 @@
    "outputs": [],
    "source": [
     "# You can change the GP hyperparameters here again\n",
-    "model.covar_module.base_kernel.lengthscale = 0.5\n",
+    "model.covar_module.base_kernel.lengthscale = 0.1\n",
     "model.covar_module.outputscale = 0.5  # signal variance\n",
-    "model.likelihood.noise_covar.noise = 0.5"
+    "model.likelihood.noise_covar.noise = 0.02"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "910e9471",
    "metadata": {
+    "scrolled": true,
     "slideshow": {
      "slide_type": "-"
     }
@@ -1254,7 +1255,7 @@
    },
    "outputs": [],
    "source": [
-    "acq_UCB = UpperConfidenceBound(model, beta=4)\n",
+    "acq_UCB = UpperConfidenceBound(model, beta=100)\n",
     "plot_acq_with_gp(model, observations_x, observations_y, acq_UCB, test_X, show_true_f=True, \n",
     "                 true_f_x= objective_x, true_f_y=objective_y)"
    ]
@@ -1293,6 +1294,7 @@
    "execution_count": null,
    "id": "ccb09c56",
    "metadata": {
+    "scrolled": true,
     "slideshow": {
      "slide_type": "slide"
     }
@@ -1412,7 +1414,7 @@
    "source": [
     "<h3 style=\"color:#e6541a;\">Get familiar with the Gym environment</h3>\n",
     "<p style=\"color:#e6541a;\">$\\implies$ Change the magnet values, i.e. the actions</p>\n",
-    "<p style=\"color:#e6541a;\">$\\implies$ The actions are normalized to 1, so valid values are in the [0, 1] interval</p>\n",
+    "<p style=\"color:#e6541a;\">$\\implies$ The actions are normalized to 1, so valid values are in the [-1, 1] interval</p>\n",
     "<p style=\"color:#e6541a;\">$\\implies$ The values of the <code>action</code> list in the cell below follows this magnet order: [Q1, Q2, CV, Q3, CH]</p>\n",
     "<p style=\"color:#e6541a;\">$\\implies$ Observe the plot below, what beam does that magnet configuration yield? can you center and focus the beam by hand?</p>"
    ]
@@ -1428,8 +1430,8 @@
    },
    "outputs": [],
    "source": [
-    "action = [0.5, 0.5, 0.5, 0.5, 0.5]\n",
-    "action = np.array(action)"
+    "action = # fill here\n",
+    "action = np.array(action) # [Q1, Q2, CV, Q3, CH]"
    ]
   },
   {
@@ -1528,7 +1530,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "target_beam = [#fill here!]"
+    "target_beam = [0, 1e-4, 0, 1e-4]#fill here!]"
    ]
   },
   {
@@ -1705,7 +1707,7 @@
     "<h2>Let's apply Bayesian optimization to this problem</h2>\n",
     "\n",
     "- We will use the loop implemented in the cell above\n",
-    "- In order to quantify how the algorithm is performing, we will use the __log maximum aboslute error (L1 error)__ as metric:\n",
+    "- In order to quantify how the algorithm is performing, we will use the __log mean aboslute error (L1 error)__ as metric:\n",
     "\n",
     "$$\\begin{aligned}\n",
     "f(x) &= -\\log(\\mathrm{MAE}(b_\\mathrm{current},b_\\mathrm{target})) \\\\\n",
@@ -1791,7 +1793,7 @@
     "beta = 2.0\n",
     "acquisition = \"UCB\"\n",
     "\n",
-    "opt_info = bayesian_optimize(env, observation, n_steps=40, acquisition=acquisition, beta=beta,\n",
+    "opt_info = bayesian_optimize(env, observation, n_steps=50, acquisition=acquisition, beta=beta,\n",
     "                             max_step_size=0.3, show_plot=True, time_sleep=0.05)  "
    ]
   },