Ai coding challenges

Practise ai with 47 coding challenges, from easy to hard. Every challenge runs in your browser with instant tests, an AI review of your code and community solutions to compare.

Easy · 19 Medium · 24 Hard · 4

Skills you'll practise: Gradient descentBackpropagationChain ruleDecision treesRegressionTransformersA* searchActivationsAdamAlpha-beta pruningAttentionBPE
  • Python · C++ · C#
  • Automated tests
  • AI code review
  • Community solutions
226
Challenges
2
Solutions shared
3
Languages

All challenges

Search by topic, language, or difficulty.

47 challenges
Medium

K-Means Clustering

Group points into k clusters by repeatedly assigning them to the nearest centroid and moving the centroids.

You'll learn ClusteringCentroids
aimachine learning
No solutions yet
Medium

Naive Bayes Classifier

Predict a class from categorical features with Bayes' theorem and Laplace smoothing.

You'll learn Bayes' theoremLaplace smoothing
aimachine learning
No solutions yet
Easy

Z-Score Standardization

Center a feature at 0 and scale it to a standard deviation of 1.

You'll learn StandardizationMean and std dev
aimachine learning
No solutions yet
Medium

Causal (Masked) Self-Attention

Implement the masked attention GPT models use, where each token can only look at itself and earlier tokens.

You'll learn Masked attentionGPT models
aimachine learning
No solutions yet
Easy

Softmax Function

Turn raw scores into probabilities that add up to 1, without overflowing on large values.

You'll learn SoftmaxNumerical stability
aimachine learning
No solutions yet
Easy

Matrix Multiplication

Multiply two matrices, the operation behind every layer of a neural network.

You'll learn MatricesLinear algebra
aimachine learning
No solutions yet
Easy

Word Tokenizer and Vocabulary

Split text into lowercase words and build a vocabulary sorted by frequency, the first step of any language model.

You'll learn TokenizationVocabulary building
aimachine learning
No solutions yet
Medium

Information Gain

Compute how much splitting on a feature reduces entropy, the criterion behind ID3 decision trees.

You'll learn EntropyDecision trees
aimachine learning
No solutions yet
Medium

K-Nearest Neighbors Classifier

Predict a label by majority vote of the k closest training points.

You'll learn KNNDistance metrics
aimachine learning
No solutions yet
Easy

Dot Product of Two Vectors

Multiply two vectors element by element and add the results: the core operation of every neuron.

You'll learn VectorsDot product
Neural networksaimachine learning
No solutions yet
Hard

Scaled Dot-Product Attention

Implement the attention operation at the heart of Transformers and large language models.

You'll learn AttentionTransformers
aimachine learning
No solutions yet