Avalanche Consensus
Family of probabilistic consensus protocols based on repeated random subsampling and metastability.
Family of probabilistic consensus protocols based on repeated random subsampling and metastability.
Measure of uptime and readiness of a system or service. In blockchains, relates to node liveness and data availability.
Techniques that expand training data by transforming existing samples, improving robustness and generalization.
Techniques to spot unusual patterns in data, used for fraud detection, ops alerts, and model safety.
Metric for binary classifiers representing area under the ROC curve. Higher is generally better.
Nonlinear function like ReLU or GELU that lets neural networks approximate complex relationships.
Reinforcement learning architecture with a policy network (actor) and a value estimator (critic) that learn together.
Hypothetical AI that vastly exceeds the best human minds across creativity, wisdom, and problem‑solving.
AI specialized for a specific task or domain, like image labeling or translation. Most deployed AI today.
AI that can understand, learn, and apply knowledge across most tasks at or beyond human levels.