Table 2 Output shape and number of parameters for ELM for HAM10000 and ISIC-2017 dataset.

From: Skin cancer detection through attention guided dual autoencoder approach with extreme learning machine

Layer name

HAM10000

ISIC-2017

Output shape

#Params

Output shape

#Params

Input

[1,1568]

0

[1,8192]

0

Hidden layer

[1,64]

100,416

[1,64]

524,352

Output layer

[1,7]

455

[1,2]

130

Total parameters

–

100,911

–

524,482

Back to article page