Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.
-
Updated
Dec 12, 2019 - Python
Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.
Pytorch implementations of autoregressive pixel models - PixelCNN, PixelCNN++, PixelSNAIL
Implementation of the genetic algorithm for structural break detection in time series that chooses a piecewise autoregressive model using minimum description length principle
PixelCNN implementation - based on the original version
Autoregressive Bayesian linear model
A framework based on Tensorflow for running variational Monte-Carlo simulations of quantum many-body systems.
Noise-conditional score networks for music composition by annealed Langevin dynamics
Battery SoC prediction using a RNN autoregressive architecture implemented with Pytorch
Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs
Open-AI's DALL-E for large scale training in mesh-tensorflow.
Final Project - Software Engineering 20211
🥝 Autoregressive Models in PyTorch.
PixelPyramids: Exact Inference Models from Lossless Image Pyramids (ICCV 2021)
A JAX implementation of DEformer for arbitrary conditioning.
causal decoder based on convolutions only (no attention): can be applied to ubbounded sequence lengths; the prediction of the next token depends on *all* previous tokens; allows autoregressive sampling; highly gpu-parralellizable; trained with teacher forcing;
Implementation of Metaformer, but in an autoregressive manner
A bitcoin price forecaster utilizing an ensemble of autoregressive, N-BEATS, LSTM and layer normalized models, trained on various loss functions.
Research on Image Compression using Deep Neural Networks
InfoMax-VAE pytorch implementation
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Add a description, image, and links to the autoregressive topic page so that developers can more easily learn about it.
To associate your repository with the autoregressive topic, visit your repo's landing page and select "manage topics."