Daily Dose of Data Science

Daily Dose of Data Science

Deep learning

12 Optimizers for Training Neural Networks, clearly explained!
...and what each one costs in GPU memory!
 • Avi Chawla
​Implement Knowledge Distillation from Scratch​
(must-know to efficiently run ML models in production)
 • Avi Chawla
Google solved an Old RNN Problem
A better middle ground between RNNs and Transformers.
 • Avi Chawla
A Memory-efficient Technique to Train Large Models
...that even LLMs like GPTs and LLaMAs use.
 • Avi Chawla
CPU vs GPU vs TPU vs NPU vs LPU
...explained visually!
 • Avi Chawla
16 Techniques to Optimize Neural Network Training
...explained in a single frame.
 • Avi Chawla
Researchers Solved a Decade-old Problem in Object Detection
...explained visually.
 • Avi Chawla
Build Portable ML Models with ONNX
...explained with code.
 • Avi Chawla
4 Strategies for Multi-GPU Training
...explained visually.
 • Avi Chawla
8 AI Model Architectures, Visually Explained!
must-know for AI engineers!
 • Avi Chawla
6 Types of Contexts for AI Agents
...explained from a context engineering perspective.
 • Avi Chawla
A Memory-efficient Technique to Train Large Models
...that even LLMs like GPTs and LLaMAs use.
 • Avi Chawla
© 2026 Avi Chawla · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture