.png){kind=icon}
Return
Universal activation function for machine learning
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-021-96723-8.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article proposes a universal activation function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the gradient descent algorithms are able to evolve the UAF to a suitable activation function by tuning the UAF's parameters. For the CIFAR-10 classification using the VGG-8 neural network, the UAF converges to the Mish like activation function, which has near optimal performance F-1 = 0.902 +/- 0.004 when compared to other activation functions. In the graph convolutional neural network on the CORA dataset, the UAF evolves to the identity function and obtains F-1 = 0.835 +/- 0.008. For the quantification of simulated 9-gas mixtures in 30 dB signal-to-noise ratio (SNR) environments, the UAF converges to the identity function, which has near optimal root mean square error of 0.489 +/- 0.003 mu M. In the ZINC molecular solubility quantification using graph neural networks, the UAF morphs to a Lea kyReLU/Sigmoid hybrid and achieves RMSE=0.47 +/- 0.04. For the BipedalWalker-v2 RL dataset, the UAF achieves the 250 reward in 961 +/- 193 epochs with a brand new activation function, which gives the fastest convergence rate among the activation functions.
Keywords:
NEURAL-NETWORKS
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.9
Papers:
27.8W
Citations:
83.5W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
View more