Table 3 Pre-trained and TL-based NN architectures for electrode density and mass loading prediction.

From: Transfer learning assessment of small datasets relating manufacturing parameters with electrochemical energy cell component properties

Neural Network

Target output

Number of hidden layers

Number of nodes per layer

Total number of trainable parameters

Pre-trained

Density

4

4

93

Mass loading

3

3

49

TL-based

Density

1 (plus the frozen previous layers)

4

13

Mass loading

1 (plus the frozen previous layers)

3

10

Back to article page