entering the universe
v
Videet
notes · a working notebook

Things I keep
re-explaining to myself.

A working ML notebook — architectures, training mechanics, LLMs, vision, MLOps. Each entry is something I’ve actually had to reason about, not a textbook chapter. Some pages are written. Most are stubs I’m filling in over time.

1 written·143 drafts·13 categories

Model Architecture

Classical ML, neural network families, and architectural primitives.

1/26

Data Foundations

Everything that happens to data, gradients, and loss surfaces during training.

0/25

NLP / LLMs / Agents

Language modelling, retrieval, agents, and the post-training stack.

0/28

Vision

Backbones, structural primitives, and image generation.

0/4

Speech

0/1

Multimodal AI / VLMs

Vision-language models and computer-control agents.

0/3

Offline / Online Evaluation

0/4

MLOps

0/3

On-Device AI

0/4

Project Planning

Frameworks for shipping things, on time.

0/4

Models

Specific model writeups — what they are, what they changed.

0/21

Miscellaneous

Foundations, tooling, and one-offs.

0/20

Practice

0/1

Spot an error? Reach me at videetnimsarkar21@gmail.com.