🔴 MiniSom is a minimalistic implementation of the Self Organizing Maps

PHATE (Potential of Heat-diffusion for Affinity-based Transition Embedding) is a tool for visualizing high dimensional data.

CellRank: dynamics from multi-view single-cell data

Pytorch implementation of Hyperspherical Variational Auto-Encoders

Tensorflow implementation of Hyperspherical Variational Auto-Encoders

TorchDR - PyTorch Dimensionality Reduction

TLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses

Systematically learn and evaluate the latent geometry of high-dimensional data, with a focus on scRNAseq analysis

[𝗜𝗖𝗠𝗟 𝟮𝟬𝟮𝟲] Dispersion loss counteracts embedding condensation and improves generalization in small language models

Tensorflow implementation of adversarial auto-encoder for MNIST

Pure MLX implementations of UMAP, t-SNE, PaCMAP, TriMap, DREAMS, CNE, MMAE, and NNDescent for Apple Silicon. Metal GPU for computation and video rendering.

This is the code implementation for the GMML algorithm.

Code and reuslts accompanying the NeurIPS 2022 paper with the title SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG

Code for the NeurIPS'19 paper "Guided Similarity Separation for Image Retrieval"

Dimensionality Reduction with Eilenberg-MacLane Coordinates

SPDlearn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization

Pytorch code for “Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment ” (DRMEA) (AAAI 2020).

Extended Dynamic Mode Decomposition for system identification from time series data (with dictionary learning, control and streaming options). Diffusion Maps to extract geometric description from data.

ModelCypher - Decipher the high dimensional geometry of LLMs. An open source x-ray into LLM representation structure.