IEEE Transactions on Affective Computing, 2022

A Library for Advanced Deep Time Series Models.

This repo collects effective multivariate time series clustering codes.

llama3 implementation one matrix multiplication at a time

pix2tex: Using a ViT to convert images of equations into LaTeX code.

SST-EmotionNet: Spatial-Spectral-Temporal based Attention 3D Dense Network for EEG Emotion Recognition

EEG-Based Emotion Recognition

Emotion Recognition, EEG Mapping, Azimuthal Projection Technique, CNN

The model for the paper "EEG-Based Emotion Recognition Using Regularized Graph Neural Networks"

Repository of paper "TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack" (ECAI'24)

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

This repository contains a reading list of papers on Time Series Segmentation. This repository is still being continuously improved.

Foundation Models for Time Series

A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.

A professional list of Papers, Tutorials, and Surveys on AI for Time Series in top AI conferences and journals.

Exercises from 'Introduction to Statistical Learning with Applications in R' written in Python.

Multivariate LSTM Fully Convolutional Networks for Time Series Classification

Repository for the paper 'Optimization of Data Pre-Processing Methodsfor Time-Series Classification ofElectroencephalography Data'

Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

A Library of ADMM for Sparse and Low-rank Optimization

Deep Learning for humans

The MATLAB codes for the semi-supervised feature selection method proposed in the paper "Hessian-based Semi-supervised Feature Selection using Generalized Uncorrelated Constraint".

WEASEL 2.0 - A Random Dilated Dictionary Transform for Fast, Accurate and Constrained Memory Time Series Classification

XEM: An Explainable-by-Design Ensemble Method for Multivariate Time Series Classification