Composable abstractions to build probabilistic models and inference algorithms
Random Forests for Change Point Detection
Simulation of factor model to calculate loss distribution of a credit portfolio
A simple Rust crate for handling probability distributions, primarily intended for use with Bayesian inference.
A NumPy-equivalent library for Rust — N-dimensional arrays with SIMD acceleration
Stateless Scale and Perturbation scheme for vector encryption
High-performance numerical computing with multi-backend GPU acceleration (CPU/CUDA/WebGPU)
Random number generation and distributions for ferray
Streaming anomaly detection toolkit — Random Cut Forest, per-feature drift, streaming sketches, SOC triage, hot-path ingress. Facade re-export of anomstream-core / anomstream-triage / anomstream-hotpath.
Core streaming anomaly detectors + companion primitives (Random Cut Forest, per-feature EWMA / CUSUM, drift detectors, streaming stats) — part of the anomstream toolkit
High-cadence ingress primitives (UpdateSampler, PrefixRateCap, bounded MPSC channel) for eBPF-style classifier/updater thread splits on top of anomstream-core
SOC-opinionated triage layer (Platt calibration, SAGE attribution, alert clustering, feedback, audit) on top of anomstream-core
No description provided.
No description provided.