TensorTonicTensorTonic
Problems
Study PlansLabsProjectsInterviewPricingFeedback

Implement ML Papers From Scratch

Each track breaks one landmark paper into small steps. You implement every step in Python in the browser, and tests check your code before you move on. If you are new, start with the Transformer, or read which ML papers to implement from scratch to choose a track.

Transformers and LLMs

Convolutional networks

Sequence models and embeddings

Generative models

Deep Residual Learning

Deep Residual Learning badge
1

Identity Block

Basic residual connection with no dimension change

Easy
2

Convolutional Block

Residual with 1x1 projection for dimension matching

Easy
3

Bottleneck Architecture

1×1 → 3×3 → 1×1 compression pattern

Medium
4

Skip Connection Mechanics

Gradient flow through shortcuts

Medium
5

BatchNorm in ResNet

Pre-activation vs post-activation ordering

Medium
6

Full ResNet Assembly

Combining blocks into ResNet-18/34 structure

Hard
Loading architecture visualization...