Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Training Neural Networks: the Backpropagation Algorithm

Go to class Write review

Overview

This course dives into how neural networks learn from data. You'll implement loss functions to measure prediction errors, understand the intuition and mechanics of gradient descent, master the backpropagation algorithm to calculate gradients, and use an optimizer to update network weights.

Syllabus

Unit 1: Mean Squared Error Loss

Fix the MSE Loss Function Implementation
Implementing MSE Loss with Explicit Loops
Implementing MSE Loss Function in C++
Implementing Batch Processing for MSE Loss Calculation

Unit 2: Gradient Descent Fundamentals

Implementing the Gradient Descent Update Step
Experimenting with Learning Rate in Gradient Descent
Fix the Gradient Calculation in Gradient Descent
Adding Early Stopping to Gradient Descent
Implementing the Core Gradient Descent Update Loop

Unit 3: Backpropagation in Neural Networks

Fixing the Activation Derivative in Backpropagation
Fix the Backpropagation Weight Gradient Calculation
Implementing the Backward Pass for Dense Layer Backpropagation
Gradient Shape Validation in Backpropagation

Unit 4: Backpropagation in Multi Layer Networks

Implementing MSE Loss Derivative for Backpropagation
Implementing Backpropagation Through Multiple Layers
Complete MLP Backpropagation Demo

Unit 5: Training Neural Networks

Implementing SGD Parameter Updates
Implementing Mini-Batch Data Extraction for SGD Training
Fix the SGD Update Rule
Single Training Step with SGD
Complete Training Loop with Mini-Batch SGD

Reviews

Start your review of Training Neural Networks: the Backpropagation Algorithm