Skip to main content
Link
Menu
Expand
(external link)
Document
Search
Copy
Copied
Applied Deep Learning
Home
Syllabus
Pre-work
Course Materials
Week 1: Fine-tuning and data audit
Week 2: Controlled improvement and failure analysis
Week 3: Parameter-efficient adaptation (LoRA/PEFT)
Week 4: Error diagnosis: slices, calibration, and cross-model analysis
Week 5: Quantization and decoder economics
Week 6: Distillation and final model decision
Blog
Distillation acted like a calibration regularizer. There was a cheaper one.
Your int8 Quantization Is 2.5× Slower Than fp16
No magic, but first: a transformers PR
When Better Means Worse
You Can't Scale Your Way Out of a Data Problem
Half a Percent: Thoughts and Results on Decoders for Text Classification
44% Accuracy Without a Single Training Example
Your T4 Training Is 4x Slower Than It Should Be
When Your "Ready to Use" Dataset Has the Same Category Listed Twice
What Do You Teach When Compression Doesn't Produce a Speedup?
The Questions Model Cards Don't Answer
Picking a Model for Teaching
GitHub Repo
Course Materials
Weekly lecture slides, lab notebooks, homework, and rubrics. Released before each class.
Table of contents
Week 1: Fine-tuning and data audit
Week 2: Controlled improvement and failure analysis
Week 3: Parameter-efficient adaptation (LoRA/PEFT)
Week 4: Error diagnosis: slices, calibration, and cross-model analysis
Week 5: Quantization and decoder economics
Week 6: Distillation and final model decision