Open source package for accelerated symbolic discovery of fundamental laws.

PyTorch Implementation of the paper "A Neuro-vector-symbolic architecture for Solving Raven's Progressive Matrices" published in Nature Machine Intelligence 2023.

The official implementation for ICLR23 paper "GNNSafe: Energy-based Out-of-Distribution Detection for Graph Neural Networks"

Dynamical Point Cloud Registration with Geometry-aware graph signal processing

Time series Timeseries Deep Learning Machine Learning Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

The fast Continuous Wavelet Transform (fCWT) is a library for fast calculation of CWT.

🐸 An open source efficient symbolic time series compression technique

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

SpectroMap is a peak detection algorithm that computes the constellation map for a given signal

A Python Library for Graph Outlier Detection (Anomaly Detection)

Multitaper spectrum for time-series analysis

PaddleSpatial is an open-source spatial-temporal computing tool based on PaddlePaddle.

[AAAI 2023] An official source code for paper Cluster-guided Contrastive Graph Clustering Network.

Mixed graph Laplacian upscaling and solvers

Seamless operability between C 11 and Python

A Biological Oscillations Analysis Toolkit

A package for the sparse identification of nonlinear dynamical systems from data

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

🐍 Python Implementation and Extension of RDF2Vec

The accompanying code for "Simplifying and Understanding State Space Models with Diagonal Linear RNNs" (Ankit Gupta, Harsh Mehta, Jonathan Berant).

MASS (Mueen's Algorithm for Similarity Search) - a python 2 and 3 compatible library used for searching time series sub-sequences under z-normalized Euclidean distance for similarity.

Dimensionless learning codes for our paper called "Data-driven discovery of dimensionless numbers and governing laws from scarce measurements".

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Audio Super Resolution in the Spectral Domain

Automated Time Series Forecasting

Probabilistic programming framework that facilitates objective model selection for time-varying parameter models.