Zomato

Solve a problem (pass its tests) and it's checked off here automatically — your progress is saved, so it stays checked when you come back.

• AdaBoost fit (decision stumps)EnsembleLearningBoostingMedium
• Adam optimiser stepCalculusMedium
• AdamW step (decoupled weight decay)CalculusRegularizationMedium
• The RAG run: search → ground → answerLargeLanguageModelMLSystemDesignAgenticAIMedium
• Full self-attention from XTransformersMedium
• BatchNorm forward (train + eval modes)NormalizationRegularizationMedium
• Best Gini-based split (decision tree)DecisionTreesMedium
• Train BPE merges from a corpusNaturalLanguageProcessingHard
• Multi-Head Attention (full layer)TransformersLargeLanguageModelMedium
• MSE loss + backwardNeuralNetworksCalculusLossFunctionsEasy
• Cross-Encoder Rerank Top-kLargeLanguageModelMLSystemDesignEasy
• Edge models — magnitude pruningComputerVisionNeuralNetworksMLSystemDesignEasy
• DDM Concept Drift DetectorStatisticsMLSystemDesignMedium
• Weight decay — the L2 penalty termNeuralNetworksOverfittingRegularizationEasy
• Vanishing gradients through sigmoid layersNeuralNetworksActivationFunctionsCalculusEasy
• DPO lossLargeLanguageModelLossFunctionsFineTuningMedium
• Dropout layer (forward & backward)NeuralNetworksCalculusRegularizationMedium
• Focal loss (multiclass)EvaluationMetricsLossFunctionsMedium
• Generate random subsets (bootstrap)StatisticsEnsembleLearningBaggingEasy
• Gradient Boosting: One Round (Stump)DecisionTreesEnsembleLearningBoostingMedium
• Histogram Split Finding (GBM)DecisionTreesEnsembleLearningBoostingHard
• Holt-Winters Exponential SmoothingStatisticsMedium
• Huber & Hinge lossesLinearRegressionLogisticRegressionStatisticsEasy
• k-fold cross-validationStatisticsEvaluationMetricsEasy
• Linear regression — gradient descentLinearRegressionCalculusEasy
• Logistic regression — gradient descentLinearRegressionLogisticRegressionCalculusMedium
• Logistic regression — binary cross-entropy lossLinearRegressionLogisticRegressionLossFunctionsEasy
• LoRA forward passLargeLanguageModelFineTuningEasy
• Population Stability Index (PSI)StatisticsMLSystemDesignMedium
• Reciprocal Rank Fusion (RRF)LargeLanguageModelMLSystemDesignMedium
• RMSprop optimizerCalculusEasy
• Scaled dot-product attentionTransformersMedium
• Vanishing or exploding? Classify the regimeRecurrentNeuralNetworkNeuralNetworksCalculusEasy
• Build sliding-window training pairsRecurrentNeuralNetworkStatisticsMedium
• SMOTE OversamplingStatisticsEvaluationMetricsMedium
• Two-Sample Test + p-valueStatisticsMedium
• Two-Tower Top-k RetrievalMLSystemDesignEmbeddingsEasy