ELU activation: A comprehensive analysis
Through various experiments, ELU is accepted by many researchers as a good successor of the original version (ReLU). Continue reading ELU activation: A comprehensive analysis
Tag: Activation Function
Batch Normalization and why it works
Batch Normalization (BatchNorm) is a very frequently used technique in Deep Learning, however, the reason why it works is often interpreted ambiguously. Continue reading Batch Normalization and why it works
Rectifier Linear Unit (ReLU)
Despise its simplicity, ReLU previously achieved the top performance over various tasks of modern Machine Learning. Continue reading Rectifier Linear Unit (ReLU)
Sigmoid, tanh activations and their loss of popularity
The sigmoid and tanh activation functions were very frequently used in the past but have been losing popularity in the era of Deep learning. Continue reading Sigmoid, tanh activations and their loss of popularity