Randomness in neural networks: an overview

By Simone Scardapane, Dianhui Wang. WIREs Data Mining Knowl. Discov., 2017

343 citations recorded by the source corpus.

How researchers see this paper

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

Global optimization issues in deep network regression: an overview (2018, methodology): “See [121] and the special issue [142] for overviews of the different ways in which randomization can be applied to the design of shallow FNN and the statistical learning properties of the corresponding randomized learning scheme.”
Stochastic Configuration Networks: Fundamentals and Algorithms (2017, background): “Readers may refer to a survey paper for more detail [11].”
Recent Advances in Physical Reservoir Computing: A Review (2018, background): “…refer to the following well-organized articles: the survey paper (Lukoševičius & Jaeger, 2009), the review papers (Lukoševičius & Schrauwen, 2012; Scardapane & Wang, 2017; Schrauwen, Verstraeten, & Van Campenhout, 2007), and the special issue on ESNs and LSMs in Neural Networks (Jaeger, Maass, &…”
InceptionTime: Finding AlexNet for time series classification (2019, background): “This was an important ﬁnding for us, previously observed in Scardapane and Wang (2017), as rather than training only one, potentially very good or very poor, instance of the Inception network, we decided to leverage this instability through ensembling, creating InceptionTime.”