From e09b22a2a1d174a3b63c3ff09ae6ddddf8fa1d21 Mon Sep 17 00:00:00 2001
From: judsonupchurch <judson.upchurch@gmail.com>
Date: Sun, 5 Jan 2025 18:59:24 -0600
Subject: [PATCH] Added lecture contents in readme

---
 README.md | 54 +++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 41 insertions(+), 13 deletions(-)

diff --git a/README.md b/README.md
index 70a9fa0..1f99385 100644
--- a/README.md
+++ b/README.md
@@ -3,27 +3,55 @@ Following along with the playlist created by Vizuara on Youtube (https://www.you
 
 The primary objective is to gain a foundational understanding of simple neural networks including forward propagation, activation layers, backward propagation, and gradient descent.
 
-## Lecture Contents
-Lectures 1-2 use same handout.
+# Lectures
+## Lectures 1-2
+Neurons and layers with matrices and numpy.
 
-Lectures 3-6 use same handout.
+## Lectures 3-6
+Multiple layer neural networks with matrices and numpy.
 
-Lectures 7-11 use same handout.
+ReLU and softmax activation functions.
 
-Lecture 12 uses same handout.
+## Lectures 7-11
+Cross entropy loss and optimizing a single layer with gradient descent.
 
-Lectures 13-17 use same handout.
+## Lecture 12
+Backpropagation for a single neuron.
 
-Lecture 18 uses same handout.
+## Lectures 13-17
+Backpropagation for neuron layers and activation layers.
 
-Lectures 19-21 use same handout.
+## Lecture 18
+Backpropagation on the cross entropy loss function.
 
-Lecture 22 uses same handout.
+## Lectures 19-21
+Combined backpropagation for softmax and cross entropy loss.
 
-Lectures 23-24 use same handout.
+Entire backpropagation pipeline for neural networks.
 
-Lectures 25-26 use same handout.
+Entire forward pass pipeline for neural networks.
 
-Lecture 27 uses same handout.
+## Lecture 22
+Gradient descent for entire neural network.
 
-Lectures 28-31 use same handout.
\ No newline at end of file
+## Lectures 23-24
+Learing rate decay in optimization.
+
+Momentum in training neural networks.
+
+## Lectures 25-26
+Coding the ADAGRAD optimizer for neural networks.
+
+Coding the RMSprop optimizer for neural networks.
+
+## Lecture 27
+Coding the ADAM optimizer for neural networks.
+
+## Lectures 28-31
+Neural network testing, generilization, and overfitting.
+
+K-Fold cross validation.
+
+L1/L2 regularization to avoid overfitting.
+
+Dropout layers in neural networks.
\ No newline at end of file