Table 14 The optimal architecture searched for MINST datasets except for MRDBI.

From: Fractal and chaotic map-enhanced grey wolf optimization for robust fire detection in deep convolutional neural networks

Type

Set up

Stride size

Filter size

Feature maps

Neurons

Convolution

1

1

18

 

Convolution

4

6

108

 

Convolution

4

7

107

 

Convolution

4

8

118

 

Fully-connected

 

1246

Fully-connected

 

10

Back to article page