Search Results
ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets.
Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
We propose a simple but strong baseline for time series classification from scratch with deep neural networks.
Sequencer: Deep LSTM for Image Classification
Here we propose Sequencer, a novel and competitive architecture alternative to ViT that provides a new perspective on these issues.
Ranked #20 on
Image Classification
on ImageNet V2
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Our channel-independent patch time series Transformer (PatchTST) can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models.
Ranked #1 on
Time Series Forecasting
on Electricity (192)
Multivariate Time Series Forecasting
Representation Learning
+1
