Learning resources
Tutorials, courses, and concept primers — SGD, backprop, initialization, and companion courses.
Short modern intro lecture series — good warm-up week material.
Widely used MOOC primer before diving into the research papers.
Top-down practical course — useful complement to STATS 385’s theory focus.
On-site glossary of deep learning motifs — pair with this list for vocabulary.
Lecture 1 recommended video — interactive CNN feature visualization.
He et al. — principled weight init for ReLU nets; course learning.md points here.
Basic optimizer primer — steps along the negative gradient of the loss.
Chain-rule engine for computing all parameter gradients efficiently.
Course cheat-sheet concept: SGD approximates full gradients with random minibatches.
Core textbook chapter on multilayer perceptrons; assign early.
Sibling Stanford course; outstanding notes if you need vision/architecture grounding.
Primary hands-on tutorial listed by the course — code + math together.
Generating suggestions...
This may take 5-10 seconds
Analyzing titles...
This may take 5-10 seconds