Search Results for author:
Found 4 papers, 1 papers with code
SGD method for entropy error function with smoothing l0 regularization for neural networks
Nevertheless, the network training based on this error function generally leads to a slow convergence rate, and can easily be trapped in a local minimum or even with the incorrect saturation problem in practice.
LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss
Today, a vast amount of various kinds of open-source software, which form networks of repositories, is often hosted on GitHub - a popular software development platform.
Leveraging Privacy Profiles to Empower Users in the Digital Society
Users need to manage software privacy settings properly to protect personally identifiable information and express personal ethical preferences.
Unavailable Transit Feed Specification: Making it Available with Recurrent Neural Networks
Studies on public transportation in Europe suggest that European inhabitants use buses in ca.
