SOTAVerified

Time Series Analysis

Time Series Analysis is a statistical technique used to analyze and model time-based data. It is used in various fields such as finance, economics, and engineering to analyze patterns and trends in data over time. The goal of time series analysis is to identify the underlying patterns, trends, and seasonality in the data, and to use this information to make informed predictions about future values.

( Image credit: Autoregressive CNNs for Asynchronous Time Series )

Papers

Showing 891900 of 6748 papers

TitleStatusHype
Multitask learning and benchmarking with clinical time series dataCode1
Modeling Long- and Short-Term Temporal Patterns with Deep Neural NetworksCode1
Soft-DTW: a Differentiable Loss Function for Time-SeriesCode1
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data ProcessingCode1
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence ModelsCode1
On the adoption of abductive reasoning for time series interpretationCode1
Recurrent Neural Networks for Multivariate Time Series with Missing ValuesCode1
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICACode1
Convolutional Radio Modulation Recognition NetworksCode1
Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly BenchmarkCode1
Show:102550
← PrevPage 90 of 675Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1naive classifierF187.47Unverified
2GRU-D - APC (n = 1)F127.3Unverified
3GRU-APC (n = 1)F125.7Unverified
4GRU-DF122.5Unverified
5GRUF122.3Unverified
6GRU-SimpleF122.2Unverified
7GRU-MeanF122.1Unverified
#ModelMetricClaimedVerifiedStatus
1SepTr% Test Accuracy98.51Unverified
2ViT% Test Accuracy98.11Unverified
3FlexTCN-4% Test Accuracy97.73Unverified
4MatchboxNet% Test Accuracy97.4Unverified
5CKCNN (100k)% Test Accuracy95.27Unverified
6FlexTCN-6% Test Accuracy (Raw Data)91.73Unverified
#ModelMetricClaimedVerifiedStatus
1ResBiLSTMMAE0.13Unverified