This course introduces the core building blocks of neural networks. You'll learn what a neuron is, how it processes information, the role of activation functions, and how neurons are organized into layers. By the end, you'll implement a single dense layer from scratch using R and base R matrix operations.
Overview
Syllabus
- Unit 1: Neural Networks Fundamentals: Neurons and Layers (R Edition)
- Neural Networks Fundamentals Quiz
- Unit 2: Implementing an Artificial Neuron from Scratch in R
- Initializing a Neuron in R
- Adding Input Validation to a Neuron's Forward Function
- Implementing the Forward Pass for an Artificial Neuron in R
- Using a Neuron to Process Data in R
- Unit 3: Adding Activation Functions to Our Neuron (R Edition)
- Applying the Sigmoid Activation Function to a Neuron
- Fixing the Order of Operations in a Neuron's Forward Pass
- Implementing the Sigmoid Activation Function in R
- Unit 4: Building a Dense Layer in Neural Networks with R
- Initializing Small Random Weights in a Dense Layer
- Fixing the Biases Vector in a Dense Layer
- Initializing Weights and Biases for a Dense Layer in R
- Creating and Inspecting Dense Layers in R
- Counting Parameters in a Dense Layer
- Unit 5: Forward Propagation in Dense Layers with R
- Implementing Bias Addition in Forward Propagation for a Dense Layer
- Fix Matrix Multiplication in Forward Propagation
- Completing the Forward Pass with Sigmoid Activation
- Implementing Forward Propagation in a Dense Layer with R
- Implementing Forward Propagation with a Dense Layer in R