K‑NN (k‑Nearest Neighbors)
Non‑parametric method that classifies or regresses based on the majority of nearest samples.
Non‑parametric method that classifies or regresses based on the majority of nearest samples.
Unsupervised algorithm that partitions data into k clusters by minimizing within‑cluster variance.
Distributed log used by indexers and analytics stacks to process on‑chain events at scale.
Date after which a model’s training data does not include events, requiring tools or browsing.
Technique where a smaller student model learns from a larger teacher’s soft targets or explanations.
Wallet that uses multi‑party computation to split signing across devices, avoiding a single private key.
Monitoring transactions for risk signals like sanctions exposure, mixers, or stolen funds.
Regulatory process for verifying user identity in exchanges, on‑ramps, and compliant dApps.
Encrypted JSON format that stores a private key using a KDF and cipher; often called V3 keystore.