missing minus p344; mlp img fix, jozef errata

docs/equations/pymle-equations.tex

@@ -1920,7 +1920,7 @@ In gradient descent optimization, we updated all weights simultaneously after ea
 $\mathbf{w}$ as follows:
 
 \[
-\frac{\partial}{\partial w_j} J(\mathbf{w}) = \sum_i \big( y^{(i)} - a^{(i)} \big) x_{j}^{(i)}
+\frac{\partial}{\partial w_j} J(\mathbf{w}) = - \sum_i \big( y^{(i)} - a^{(i)} \big) x_{j}^{(i)}
 \]
 
 Here $y^{(i)}$ is the target class label of a particular sample $x^{(i)}$ , and $a^{(i)}$ is the \textit{activation} of the neuron, which is a linear function in the special case of Adaline. Furthermore, we defined the \textit{activation function} $\phi(\cdot)$ as follows:

docs/errata.md

@@ -24,7 +24,7 @@ I would be happy if you just write me a short [mail](mailto:mail@sebastianraschk
 
 ## Donations
 
-- Current amount for the next donation: $12.00
+- Current amount for the next donation: $17.00
 - Amount donated to charity:
   - [$39.00 2016-04-07](./2016-04-07-unicef.pdf)
   - [$76.00 2016-03-03](./2016-03-03-unicef.pdf)
@@ -37,6 +37,7 @@ I would be happy if you just write me a short [mail](mailto:mail@sebastianraschk
 2. Christopher Galpin ($8.00)
 18. David C. ($6.00)
 2. Edgar C. ($5.00)
+27. Jozef Genzor ($5.00)
 3. S.R. ($4.00)
 3. Will P. ($4.00)
 3. Ignacio A. ($4.00)
@@ -65,6 +66,7 @@ I would be happy if you just write me a short [mail](mailto:mail@sebastianraschk
 25. Neeraj K. ($1.00)
 26. Attila B. ($1.00)
 
+
 ...
 
 # Errata