[Research Paper] A disciplined approach to neural network hyper-parameters: Part 1 – learning rate, batch size, momentum, and weight decay

Which value or method works well for NN hyperparameters?

December 13, 2024

Leave HJ’s trace, All-In

Basic Information

Authors: Leslie N. Smith
Journals: US Naval Research Laboratory Technical Report
Year: 2018
Citation: Leslie N. Smith, A disciplined approach to neural network hyper-parameters: Part 1 – learning rate, batch size, momentum, and weight decay. US Naval Research Laboratory Technical Report 5510-026 (2018).