-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Our work "AdaTime: A Systematic Evaluation of Domain Adaptation Algorithms on Time Series Data" is now public. We provide a benchmarking framework named "AdaTime" to fairly evaluate Unsupervised domain adaptation (UDA) approaches on time-series data. We find that UDA approaches proposed for visual data can be directly applied to time-series data, and still achieve excellent performance, even better than methods specially proposed for time-series UDA. Se were impressed by the consistently superior performance of "DIRT-T" method on all the datasets. We provide the code publicly on github https://github.com/emadeldeen24/AdaTime
Related posts
-
PyTorch-adapt re-purposes existing ML models to work in new domains
-
Cash-flow forecasting
-
[R] Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
-
[P] Deep Learning for time series forecasting (neuralforecast, python package)
-
SB-1047 will stifle open-source AI and decrease safety