Skip to main content
Journal of Big Data

Table 2 Momentum and batch size per dataset

From: Evaluation of maxout activations in deep learning across several big data domains

Dataset

Momentum

Batch size

MNIST

0.5

64

Fashion-MNIST

0.5

64

CIFAR-10

0.5

64

CIFAR-100

0.5

64

LFW

0.5

64

MS-Celeb

0.9

128

Medicare Part B

N/A

200

Medicare Part D

N/A

200

DMEPOS

N/A

200

Combined CMS

N/A

200

Sentiment140

N/A

200

Google Speech Commands

N/A

200

IRMAS

N/A

200

IDMT-SMT-Audio-Effects

N/A

200

Amazon4M

N/A

200

Amazon1M

N/A

200

Yelp500K

N/A

200

Yelp1M

N/A

200

Back to article page