Phase 0: Vision Foundations · ~75 minutes · Python

Convolutions from Scratch

A convolution is a tiny dense layer you slide across an image, sharing the same weights at every location.

Hiring signal: Understanding of convolutions from scratch internals

What you will learn

Implement 2D convolution from scratch using only NumPy, including the nested-loop version and a vectorised `im2col` version
Compute output spatial size for any combination of input size, kernel size, padding, and stride, and justify the `(H - K + 2P) / S + 1` formula
Hand-design kernels (edge, blur, sharpen, Sobel) and explain why each one produces the pattern of activations it does
Stack convolutions into a feature extractor and connect the depth-of-the-stack to the size of the receptive field

Introduction

Type: Build Languages: Python Prerequisites: Phase 3 (Deep Learning Core), Phase 4 Lesson 01 (Image Fundamentals) Time: ~75 minutes

Learning Objectives

Implement 2D convolution from scratch using only NumPy, including the nested-loop version and a vectorised im2col version
Compute output spatial size for any combination of input size, kernel size, padding, and stride, and justify the (H - K + 2P) / S + 1 formula
Hand-design kernels (edge, blur, sharpen, Sobel) and explain why each one produces the pattern of activations it does
Stack convolutions into a feature extractor and connect the depth-of-the-stack to the size of the receptive field

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build It, Use It, Ship It, Exercises, Key Terms, Further Reading — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.