Small fixes

src/year1/cognition-and-neuroscience/module1/sections/_nervous_system.tex

@@ -220,12 +220,6 @@ In a neuron, there are four regions that handle signals:
         \includegraphics[width=0.8\textwidth]{./img/neuron_transmission.png}
         \caption{Transmitting regions of different types of neurons}
     \end{figure}
-
-    \begin{figure}[h]
-        \centering
-        \includegraphics[width=0.8\textwidth]{./img/neuron_transmission2.png}
-        \caption{Signal from the input to the output zones}
-    \end{figure}
 \end{descriptionlist}
 
 
@@ -292,6 +286,16 @@ In a neuron, there are four regions that handle signals:
                         \end{remark}
                 \end{enumerate}
 
+                \begin{figure}[h]
+                    \centering
+                    \includegraphics[width=0.8\textwidth]{./img/neuron_transmission2.png}
+                    \caption{
+                        \parbox[t]{0.6\linewidth}{
+                            Signal from the input to the output zone. The amplitude of the stimulus modulates the frequency of \ac{ap}.
+                        }
+                    }
+                \end{figure}
+
                 \begin{figure}[H]
                     \begin{subfigure}{.45\textwidth}
                         \centering
@@ -310,7 +314,7 @@ In a neuron, there are four regions that handle signals:
         \begin{remark}
             As the signal is constantly regenerated, 
             \Acp{ap} have similar amplitude and duration in all neurons, regardless of the characteristics of the input \acp{psp}.
-            Therefore, the only way an \ac{ap} has to carry information is by varying frequency and firing duration, making it a binary signal.
+            Therefore, the only way an \ac{ap} has to carry information is by varying frequency depending on the stimulus intensity, making it a binary signal.
         \end{remark}
 \end{description}
 

src/year1/image-processing-and-computer-vision/module2/sections/_classification.tex

@@ -332,7 +332,7 @@ The prediction is obtained as the index of the maximum score.
         \]
         where:
             \begin{itemize}
-                \item $\matr{\theta} = (W_1 \in \mathbb{R}^{h \times i}, b_1 \in \mathbb{R}^{h}, W_2 \in \mathbb{R}^{c \times h}, b_2 \in \mathbb{R}^{c})$
+                \item $\matr{\theta} = (\matr{W}_1 \in \mathbb{R}^{h \times i}, \vec{b}_1 \in \mathbb{R}^{h}, \matr{W}_2 \in \mathbb{R}^{c \times h}, \vec{b}_2 \in \mathbb{R}^{c})$
                     are the parameters of the linear transformations with an inner representation of size $h$.
                 \item $\phi$ is an activation function.
                 \item $\vec{h}$ and $\vec{s}$ are activations.