ACTIVATION FUNCTIONS IN NEURAL NETWORKS
By Siddhartha Sharma, Simone Sharma, Anidhya Athaiya. International Journal of Engineering Applied Sciences and Technology, 2020
1,198 citations recorded by the source corpus.
—Artificial Neural Networks are inspired from the human brain and the network of neurons present in the brain. The information is processed and passed on from one neuron to another through neuro synaptic junctions. Similarly, in artificial neural networks there are different layers of cells arranged and connected to each other. The output/information from the inner layers of the neural network are passed on to the next layers and finally to the outermost layer which gives the output. The input to the outer layer is provided non-linearity to inner layers’ output so that it can be further processed. In an Artificial Neural Network, activation functions are very important as they help in learning and making sense of non-linear and complicated mappings between the inputs and corresponding outputs.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/50fdddde4a86fc6f2e23fd7ccbf60e6a37fc4c6d
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
- Simone Scardapane
- Valerio Marsocci
- Nikos Komodakis
- Quoc V. Le
- Alan L. Yuille
- Dacheng Tao
- Yoshua Bengio
- Barret Zoph
Citations in the corpus
- MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing (2021, methodology): “the original paper [18], we introduce a slight modification to the original architecture: ReLU activation function was replaced with a leaky-ReLU, that seems to be more stable, avoiding zero gradient flows for some neurons [59].”