A review on neural networks with random weights

470 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.

Dataset Condensation with Distribution Matching (2021, background): “First, randomly initialized networks are reported to produce powerful representations for multiple computer vision tasks [36, 9, 2].”
A review on weight initialization strategies for neural networks (2021, background): “A review of literature focussing on the analysis based on universal approximation of such mechanism has been presented by Wang and Cao (2018).”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, background): “In recent years, there have been many efforts to optimize algorithms for training ML models efficiently on large datasets [183,184,186,187].”