Table 1 Key hyperparameters used in the proposed attention-based DL model for intelligent threat detection in IoT networks.

From: Advances in IoT networks using privacy-preserving techniques with optimized multi-head self-attention model for intelligent threat detection based on plant rhizome growth optimization

Component

Hyperparameters

Values

CNN

Filters, kernel size, activation

64, 3 × 3, ReLU

BiGRU

Units, layers, dropout

128, 2, 0.3

MHSAM

Attention heads, attention dimension

8, 64

Training settings

Optimizer, learning rate, batch size, epochs

Adam, 0.001, 64, 50

Back to article page