The State of the Art

By Greg Richards. 2001

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

Citations in the corpus

DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks (2017, background): “…produces accurate probabilistic forecasts across a range of input characteristics, thus showing that modern deep learning-based approaches can effective address the probabilistic forecasting problem, which is in contrast to common belief in the ﬁeld and the mixed re-sults reported in [23, 16].”
Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, background): “As from short individual series the amount of information that can be extracted is limited, more complex methods that may have smaller bias will suffer from large variance, and finally end up performing worse (Zhang et al., 1998; Yan, 2012).”
Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application (2013, methodology): “The following normalise equation is used (Zhang et al. 1998): znorm ¼ zo zzmax zmin ð7Þ where znorm = normalised value; z0 = original value; z = mean; zmax = maximum value; and zmin = minimum value.”
Toward Automatic Time-Series Forecasting Using Neural Networks (2012, methodology): “[1], have already looked at the pattern identification problem.”
Laboratory diagnosis of emerging human coronavirus infections – the state of the art (2020, background): “For the clinical diagnostic application, the genetic heterogeneity of HCoVs precludes a single "pan-HCoV" molecular assay [48] [49] [50] [51] ( Table 2 ).”