The effect of activation functions on accuracy, convergence speed, and misclassification confidence in CNN text classification: a comprehensive exploration.
Rebecca H. K. EmanuelPaul David DochertyHelen LuntKnut MöllerPublished in: J. Supercomput. (2024)
Keyphrases
- convergence speed
- text classification
- activation function
- learning rate
- differential evolution
- convergence rate
- particle swarm optimization algorithm
- particle swarm optimization
- pso algorithm
- feature selection
- hidden layer
- text mining
- neural network
- artificial neural networks
- text categorization
- feed forward
- labeled data
- knn
- training speed
- particle swarm optimization pso
- steady state error
- rbf neural network
- state space
- data mining