Initialization of Network Parameters

By A. Ghatak. 2019

9 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Optimization & Training

How researchers see this paper

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

In Artificial Intelligence

1. Martin Strobel
2. Hong Chang
3. Reza Shokri
4. Prakhar Ganesh
5. Prateek Mittal
6. Liwei Song
7. Lingjuan Lyu
8. Yang Zhang

In Optimization & Training

1. Hong Chang
2. Reza Shokri

Citations in the corpus

• On The Impact of Machine Learning Randomness on Group Fairness (2023, background): “Randomness in weight initialization is crucial for breaking the symmetry between model parameters and allows the neural network to learn complex functions [25].”