What is it about?
Make Artificial Neural Network more like the biological brain structure in sight of Activation Function.
Featured Image
Photo by Uriel SC on Unsplash
Why is it important?
We think the learnable activation function in each cells play a important role to make brain learning high effective, especially in generalization capability and robustness. This work bring this mechanism into ANN, and improved its performance based on some experiment data, so it has important science research value.
Read the Original
This page is a summary of: A Self-Adaptive and Multiple Activation Function Neural Network for Facial Expression Recognition, October 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3501409.3501605.
You can read the full text:
Contributors
The following have contributed to this page
