autoregressive

Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"

Open-AI's DALL-E for large scale training in mesh-tensorflow.

A list of awesome resources on normalizing flows.

PyAF is an Open Source Python library for Automatic Time Series Forecasting built on top of popular pydata modules.

End-2-end speech synthesis with recurrent neural networks

PyTorch implementation of "Conditional Image Generation with PixelCNN Decoders" by van den Oord et al. 2016

A framework based on Tensorflow for running variational Monte-Carlo simulations of quantum many-body systems.

Simulate stochastic timeseries that follow ARFIMA, ARMA, ARIMA, AR, etc. processes

Score-driven models, aka generalized autoregressive score models, in Julia

Pytorch implementations of autoregressive pixel models - PixelCNN, PixelCNN++, PixelSNAIL

Julia package containing utilities intended for Time Series analysis.

Forecasting Monthly Sales of French Champagne - Perrin Freres

Autoregressive Bayesian linear model

PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.

InfoMax-VAE pytorch implementation

R package to estimate time-varying coefficient regressions

Light, modular framework for dynamic time series modeling, compatible with scikit-learn

Battery SoC prediction using a RNN autoregressive architecture implemented with Pytorch

Noise-conditional score networks for music composition by annealed Langevin dynamics

A Repo of Time-series analysis techniques. Holt-Winter methods, ACF/PACF, MA, AR, ARMA, ARIMA, SARIMA, SARIMAX, VAR, VARMA, RNN Keras, Facebook- Prophet etc.

Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.

List of papers and code for relevant Generative Models

Auto Regressive Models applied on Paris Subway Stations. Time Series Analysis. Predictions of affluence.

Statistical Learning Models for Damage Detection in Civil Structures.

Abstract: The S&P500 is difficult to predict. Multi-factor models provide a useful framework for making returns predictions and for controlling portfolio risk. This paper explores a three-step process in predicting PCA and Autoencoders factors to generate multi-factor models from the S&P500 component securities.

Personal GitHub

Personal Website

Time series predictive model to forecast the airline monthly passenger

This repository contains several smaller projects and tutorials that I've created for fun about time series analysis in R.