Update documentation

_sources/lecture/gradients.md

@@ -93,7 +93,7 @@ Reverse-mode differentiation. (Source: {cite}`maclaurin2016`, Section 2)
 
 Given is the linear model $h(x)=w \cdot x+b$ that maps from the input $x\in \mathbb{R}$ to the output $y\in \mathbb{R}$, as well as a dataset of a single measurement pair $\{(x=1, y=7)\}$. The initial model parameters are $w=2, b=3$. Compute the gradient of the MSE loss w.r.t. the model parameters, and run one step of gradient descent with step size $0.1$. Draw all intermediate values in the provided compute graph below.
 
-```{figure} ../imgs/gradients/ad_example_question.png
+```{figure} ../imgs/gradients/gradients_example_question.png
 ---
 width: 600px
 align: center
@@ -114,7 +114,7 @@ x &= 1; \; w=2; \; b=3; \; y=7 \\
 \end{align}
 $$ (ad_example_forward)
 
-```{figure} ../imgs/gradients/ad_example_solution.png
+```{figure} ../imgs/gradients/gradients_example_solution.png
 ---
 width: 600px
 align: center

exercise/bayes.html

@@ -664,8 +664,8 @@ <h3><span class="section-number">2.1.4. </span>Bayesian Linear Regression Model<
 <p>The model below essentially makes the following prior assumptions:</p>
 <div class="math notranslate nohighlight">
 \[y \approx h(x) = wx + b + \epsilon, \quad \text{with:}\]</div>
-<div class="amsmath math notranslate nohighlight" id="equation-f32170e5-ffb0-457e-840a-2ee94804d3ea">
-<span class="eqno">(2.30)<a class="headerlink" href="#equation-f32170e5-ffb0-457e-840a-2ee94804d3ea" title="Permalink to this equation">#</a></span>\[\begin{align}
+<div class="amsmath math notranslate nohighlight" id="equation-762ca762-c6e7-49ee-ae7d-1206a8e34025">
+<span class="eqno">(2.30)<a class="headerlink" href="#equation-762ca762-c6e7-49ee-ae7d-1206a8e34025" title="Permalink to this equation">#</a></span>\[\begin{align}
 y_i &amp;\sim \mathcal{N}(\mu, \sigma^2)\\
 \mu &amp;= w \cdot x_i + b\\
 w &amp;\sim \mathcal{N}(0,1^2)\\

lecture/gradients.html

@@ -512,7 +512,7 @@ <h3><span class="section-number">8.2.2. </span>Reverse-Mode Differentiation (Bac
 <p><strong>Example: AD on a Linear Model</strong></p>
 <p>Given is the linear model <span class="math notranslate nohighlight">\(h(x)=w \cdot x+b\)</span> that maps from the input <span class="math notranslate nohighlight">\(x\in \mathbb{R}\)</span> to the output <span class="math notranslate nohighlight">\(y\in \mathbb{R}\)</span>, as well as a dataset of a single measurement pair <span class="math notranslate nohighlight">\(\{(x=1, y=7)\}\)</span>. The initial model parameters are <span class="math notranslate nohighlight">\(w=2, b=3\)</span>. Compute the gradient of the MSE loss w.r.t. the model parameters, and run one step of gradient descent with step size <span class="math notranslate nohighlight">\(0.1\)</span>. Draw all intermediate values in the provided compute graph below.</p>
 <figure class="align-center" id="ad-example-question">
-<a class="reference internal image-reference" href="../_images/ad_example_question.png"><img alt="../_images/ad_example_question.png" src="../_images/ad_example_question.png" style="width: 600px;" /></a>
+<a class="reference internal image-reference" href="../_images/gradients_example_question.png"><img alt="../_images/gradients_example_question.png" src="../_images/gradients_example_question.png" style="width: 600px;" /></a>
 <figcaption>
 <p><span class="caption-number">Fig. 8.3 </span><span class="caption-text">AD example.</span><a class="headerlink" href="#ad-example-question" title="Permalink to this image">#</a></p>
 </figcaption>
@@ -529,7 +529,7 @@ <h3><span class="section-number">8.2.2. </span>Reverse-Mode Differentiation (Bac
 \end{align}
 \end{split}\]</div>
 <figure class="align-center" id="ad-example-solution">
-<a class="reference internal image-reference" href="../_images/ad_example_solution.png"><img alt="../_images/ad_example_solution.png" src="../_images/ad_example_solution.png" style="width: 600px;" /></a>
+<a class="reference internal image-reference" href="../_images/gradients_example_solution.png"><img alt="../_images/gradients_example_solution.png" src="../_images/gradients_example_solution.png" style="width: 600px;" /></a>
 <figcaption>
 <p><span class="caption-number">Fig. 8.4 </span><span class="caption-text">AD example, solution.</span><a class="headerlink" href="#ad-example-solution" title="Permalink to this image">#</a></p>
 </figcaption>