computer-vision

Training discipline for vision models -- splits, augmentation, overfitting

taught

Running a vision model's training loop responsibly -- train/validation/ test splits, data augmentation to fight overfitting, and reading a loss curve to diagnose which failure mode is happening -- as the practical half of training a CNN this course owns locally.

Taught in

Training discipline: splits, augmentation, and overfitting
Computer Vision

Requires

gradient-descent-dl recommended
deep-learning ch.09-10 derive the update rule and backpropagation this training loop runs; this course's own quizzes only require the working-depth version taught locally.

Required by

Nothing in the catalog needs this yet.

Local knowledge map

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.