correct parameter update rule

slides/slides.qmd

@@ -181,12 +181,12 @@ $$
 :::: {#placeholder}
 ::::
 
-$$m_{n + 1} = -m_{n}\frac{dL}{dm} \cdot l_{r}$$
+$$m_{n + 1} = m_{n} - \frac{dL}{dm} \cdot l_{r}$$
 
 :::: {#placeholder}
 ::::
 
-$$c_{n + 1} = -c_{n}\frac{dL}{dc} \cdot l_{r}$$
+$$c_{n + 1} = c_{n} - \frac{dL}{dc} \cdot l_{r}$$
 
 :::: {#placeholder}
 ::::
@@ -219,7 +219,7 @@ To fit a model we need:
 
 ## Fully-connected neural networks {.smaller}
 
-- The simplest neural networks commonly used are generally called fully-connected nerual nets, dense networks, multi-layer perceptrons, or artifical neural networks (ANNs).
+- The simplest neural networks commonly used are generally called fully-connected neural nets, dense networks, multi-layer perceptrons, or artifical neural networks (ANNs).
 
 :::: {.columns}
 ::: {.column width=40%}
@@ -255,7 +255,7 @@ Image source: [3Blue1Brown](https://www.3blue1brown.com/topics/neural-networks)
 
 # Python and PyTorch {.smaller}
 
-- In this workshop-lecture-thing, we will implement some straightforward neural networks in PyTorch, and use them for different classification and regression problems.
+- In this workshop, we will implement some straightforward neural networks in PyTorch, and use them for different classification and regression problems.
 - PyTorch is a deep learning framework that can be used in both Python and C++.
   - I have never met anyone actually training models in C++; I find it a bit weird.
 - See the PyTorch website: [https://pytorch.org/](https://pytorch.org/)