An Optimized Hyperparameter of Convolutional Neural Network Algorithm for Bug Severity Prediction in Alzheimer’s-Based IoT System

Table 4

Details of hyperparameter of CNN classifier that are optimized.

Hyper-parameters	Values
Activation function	Softmax, Softplus, Softsign, ReLU, tanh, sigmoid, hard_sigmoid, linear
Optimizer parameters	Adam, Adadelta, Adagrad, Adamax, NAdam, SGD, RMSprop
Kernel initializers	Uniform, lecun_uniform, normal, zero, glorot_normal, he_normal, glorot_uniform, he_uniform
Learning rate	0.01 to 0.5
Batch size	32 and 64