Forward Pass as Matrix Multiplication

Linear Algebra for Machine Learning · Axiom Academy

Complete Forward Pass Through 2-Layer Network Full numerical walkthrough with actual numbers Hidden layer: 2 neurons (ReLU activation) Output layer: 1 neuron (no activation, regression) Step 1: Layer 1 Linear Transform Both values were positive, so ReLU just passes them through. Step 3: Layer 2 Linear Transform In the forward pass above, what are the dimensions of W¹x? If we had 5 samples instead of 1, what would X shape be for batch processing? What is the total number of trainable parameters in this network? Unit 8: Linear Algebra in Neural Networks | Module 4: Forward Pass Example

This is the written version of the interactive lesson above. See the full Linear Algebra for Machine Learning course.