A high-performance distributed deep learning system targeting large-scale and automated distributed training.

Implements "Clustering a Million Faces by Identity"

Time-HD-Lib: A Library for High-Dimensional Time Series Forecasting

Deprecated in favour of TopoMetry: https://github.com/davisidarta/topometry

Simple and efficient Python package for modeling d-dimensional Bravais lattices in solid state physics.

DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems

A numerical library for High-Dimensional option Pricing problems, including Fourier transform methods, Monte Carlo methods and the Deep Galerkin method

Bayesian optimization with Standard Gaussian Processes on high dimensional benchmarks

[TMLR' 24] High-dimensional Bayesian Optimization via Covariance Matrix Adaptation Strategy

KNRScore is a Python package for computing K-Nearest-Rank Similarity, a metric that quantifies local structural similarity between two maps or embeddings.

[AAAI' 25] BOIDS: High-dimensional Bayesian Optimization via Incumbent-guided Direction Lines and Subspace Embeddings

Video Input Generative Adversarial Imitation Learning

Holographic vectors you can compute with. Bind structure, bundle sets, unbind components cross NumPy, PyTorch, and JAX.

[ECAI' 25]: MOCA-HESP: Meta High-dimensional Bayesian Optimization for Combinatorial and Mixed Spaces via Hyper-ellipsoid Partitioning

A q-quantile estimator for high-dimensional distributions

Locally Sensitive Hashing based embedding for High Dimensional Multivariate Time Series

Reference implementation of the Spiral–HDAG–Coupling architecture. It combines a verifiable ledger, a tensor-based Hyperdimensional DAG, and Time Information Crystals to provide a new kind of memory layer for Machine Learning. With integrated Zero-Knowledge ML, the system enables trustworthy, auditable, and privacy-preserving AI pipelines.

High Dimensional Orthogonal Vectors Analysis

Lossless conversion algorithm for converting Cortical Learning Algorithm binary vectors to Modular Composite Representation vectors. Implements Integer Sparse Distributed Memory.

A Bayesian multiscale deep learning framework for flows in random media