Sharpen your ML fundamentals

master machine learning
through code

practice the mathematics, engineering and theory behind modern ML systems.

browse problems →explore topics
8 problems6 topics solvedPython

Topics

fundamentals
Tensors, arrays, NumPy basics — the building blocks every ML practitioner needs.
1
linear algebra
Vectors, matrices, eigenvalues and decompositions at the heart of ML.
3
atatistics
Probability, distributions, inference and the math behind model evaluation.
1
ml engineering
Data pipelines, training loops, optimisation and production deployment.
0
deep learning
Neural networks, backpropagation, modern architectures and training techniques.
3
interview prep
Curated ML interview questions from top research labs and tech companies.
0

Problems

TitleDifficultyTagsAcceptance
1Hello TensorEasy
NumPyArrays
2Dot ProductEasy
VectorsLinear AlgebraNumPy
3Matrix MultiplyEasy
MatricesLinear AlgebraNumPy
4Sigmoid FunctionEasy
Activation FunctionsNeural NetworksNumPy
5Mean Squared ErrorEasy
Loss FunctionsStatisticsRegression
6SoftmaxMedium
Activation FunctionsNeural NetworksNumPy
7Euclidean DistanceEasy
VectorsLinear AlgebraDistance Metrics
8Layer NormalisationHard
NormalisationBackpropagationNumPyTransformers
G
Guest User
Local progress · not synced
Progress
Easy0/60%
Medium0/10%
Hard0/10%
View full profile →