Computer Vision
Pixels, filters, feature maps and the convolutional stack that turns an image into a prediction.
About this track
A convolutional network is usually drawn as a row of coloured boxes that explains nothing. This track takes the boxes apart: what a filter is, what it produces, why the output shrinks, what padding restores, and what a stride costs you.
It starts with how an image is stored at all - grayscale intensities, then RGB channels - and finishes on the practical layer: augmentation, data loaders and transfer learning.
All 16 modules, in teaching order
- 01How Neural Networks Process ImagesLearn how Neural Networks process images by flattening 2D pixels into 1D arrays with this interactive visualization on VizLearn.
- 02Grayscale Image ProcessingSee a grayscale image for what it is: a grid of brightness numbers you can filter, threshold and edit directly.
- 03RGB Image ProcessingSplit a colour image into red, green and blue channels and see how three grids of numbers combine into every pixel.
- 04Real-time Edge DetectionSlide a sensitivity threshold across a real image and watch edges appear wherever brightness changes sharply enough.
- 05Convolutional LayerDrag a convolution filter across an image and watch it build a feature map one value at a time, the core operation inside a CNN.
- 06Padding in CNNLearn how Padding works in Convolutional Neural Networks with an interactive visualizer showing 'Valid' vs 'Same' padding on VizLearn.
- 07Strides in CNNLearn how Strides work in Convolutional Neural Networks with an interactive visualizer showing how step size downsamples feature maps on VizLearn.
- 08Parameter Sharing in CNNLearn what Parameter Sharing is in Convolutional Neural Networks and why it makes deep learning efficient on VizLearn.
- 09ReLU Activation in CNNLearn how the ReLU (Rectified Linear Unit) activation function works in Convolutional Neural Networks with this interactive visualizer on VizLearn.
- 10Pooling LayerShrink a feature map with max, average or min pooling and see how downsampling keeps the signal but discards the detail.
- 11Fully Connected Layer in CNNLearn how Fully Connected (Dense) Layers work in Convolutional Neural Networks with an interactive visualizer on VizLearn.
- 12Calculating Parameters in CNNLearn how to calculate the number of parameters in Convolutional Neural Networks with this interactive visualizer on VizLearn.
- 13CNN ArchitectureExplore a convolutional neural network layer by layer in 3D - see how filters, feature maps and pooling turn pixels into predictions.
- 14Data Loaders in CNNLearn how Data Loaders work in Convolutional Neural Networks, why we use batches, and how shuffling and augmentation impact training.
- 15Image Data AugmentationFlip, rotate, zoom and add noise to an image, and see how augmentation multiplies a small training set into a larger one.
- 16Transfer Learning with CNNLearn how Transfer Learning works in Convolutional Neural Networks, select models, and selectively unfreeze layers for fine-tuning.