Vizuara AI Labs

Vizuara AI Labs

Home
AI/ML Course Library
The Transformers
A complete architectural breakdown of Transformers, paired with a step-by-step guide to coding BERT from the ground up.
 • Mayank Pratap Singh
Vision Transformers
Understanding and fine-tuning Vision Transformers (ViT) for image classification, to hands-on transfer learning with pretrained models.
 • Mayank Pratap Singh
Teach your neural network to "respect" Physics
Physics Informed Neural Networks (PINN)
 • Vizuara AI Labs and Sreedath Panat
Gradient Descent: An Introduction to Optimization in ML
Optimization in machine learning is like tuning a guitar: you need to know the method and have the intuition.
 • Vizuara AI Labs and Sreedath Panat
ResNet: The architecture that changed ML forever
Legendary ML paper with 250,000+ citations
 • Vizuara AI Labs and Sreedath Panat
Segment Anything Model (SAM)
The promptable foundation model revolutionizing zero-shot image segmentation through massive-scale training.
 • Mayank Pratap Singh and Sreedath Panat
TurboQuant: The Surprisingly Simple Trick That's Changing How We Compress LLMs
A first-principles walkthrough of the key idea behind Google's viral quantization paper
 • Vizuara AI Labs
Build strong foundations to transition to ML
Focus on depth. Not fluff.
 • Vizuara AI Labs and Sreedath Panat
Stochastic Gradient Descent from Scratch
With a recap of vanilla/normal/batch gradient descent
 • Vizuara AI Labs and Sreedath Panat
Introduction to VLMs
Vision Language Models
 • Vizuara AI Labs and Sreedath Panat
What exactly is a VLM (Vision-Language Model)?
How does it work and how can you build one from scratch?
 • Sreedath Panat
Knowledge Distillation & Data-Efficient Image Transformers
The original ViT needed 300 million images to outperform CNNs. DeiT does it with just 1.2 million, by letting a CNN teacher distill its visual…
 • Mayank Pratap Singh
© 2026 Banque Populaire · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture