Learn Machine Learning
through code

Name: TensorTonic
Author: TensorTonic

Implement 1,300+ algorithms from scratch, from foundational ML to CUDA kernels, with the math, visualizations, and research papers behind them.

Explore problems

PythonNumPyPyTorchCUDATriton

gradient_descent.py

Loss surface $L(\mathbf{w})$

step 0|loss 24.250

$\nabla L(\mathbf{w})$ is correct
$L(w_{k+1}) < L(w_k)$ every step
$\mathbf{w} \to 0$ converges

Trusted by users from

The complete ML engineering platform

linear_regression.py

loss L(w)|rolling down the gradient

import numpy as np

def linear_regression(X, y, lr=0.01):
    w, b = 0.0, 0.0
    for _ in range(100):
        err = w * X + b - y
        w -= lr * (err * X).mean()
        b -= lr * err.mean()
    return w, b

Browse 1,300+ problems

ML algorithms

Systems and GPU programming

AI Research Papers

Agentic Systems

Mathematics for ML

ML system design

Try the problems

Cosine similarity

Direction reveals how similar two vectors are. Change the angle and compare their alignment.

\cos(\mathbf{a},\mathbf{b})=\frac{\mathbf{a}\cdot\mathbf{b}}{\lVert\mathbf{a}\rVert\lVert\mathbf{b}\rVert}

Cosine similarity0.7071

Angle between vectors45.00

Vector lengths1

What learners are saying

50,000+

learners worldwide

1Million+

code submissions

1,000+

problems to solve

Tiya on X: solved 3 TensorTonic questions and found it really fun and cool

Hao Hoang on LinkedIn: TensorTonic is LeetCode for ML Engineers

Kalyan KS on LinkedIn: Learn ML through code, LeetCode for ML

Priyansh Agarwal on X: This is just absolutely amazing

Nikunj Bhardwaj on X: 50-day streak unlocked at TensorTonic

sourav on LinkedIn: LeetCode for Machine Learning

TechFollow on X: Arav Srinivas followed TensorTonic

Umaa Maheswaran on LinkedIn: basically LeetCode but for Machine Learning

Plans

Free

$0forever

Start building your ML foundations

Unlimited code submissions
500+ problems
35 CUDA / GPU kernel problems
Interactive visualizations
Theory content per problem
13 research paper implementations
ML Math blogs
Community Discord access
Structured study plans
Real-time interview mock assessments
ML System Design problems

Start free

Pro

$12/month

or $100/yr · save 31%

Everything in Free
Structured roadmap study plansPandas, NumPy, PyTorch, SQL FoundationsLinear Algebra, Probability, Calculus, OptimizationML, DL, NLP, RL, CV specializations
500+ quiz questions across 12 modules
Real-time interview mock assessmentsData Scientist, ML Engineer, AI EngineerResearch Engineer, GPU and Performance
Priority support
ML System Design problems
Modern LLM architectures like GPT2, DeepSeek

Get Pro

Questions, answered

Is TensorTonic free to use?

TensorTonic has more than 500 problems, CUDA and GPU kernel exercises, 13 research paper implementations, and the full ML Math library completely free. Premium plans add structured study plan roadmaps, ML system design, and interview preparation.

Stop watching.
Start building.

Don't just watch ML theory. Implement it yourself, one algorithm at a time, and understand it in depth.

Create free account Browse problems

1,300+ problemsReal cloud GPUsLive AI sandboxes

Learn Machine Learning
through code