Skip to main content

Table 6 Architectures of MLP, CNN_2D, and CNN_1D

From: High-dimensional aerodynamic data modeling using a machine learning method based on a convolutional neural network

Model

MLP

CNN_2D

CNN_1D

Layer type

Parameter

Layer type

Parameter

Layer type

Parameter

Input

-

109×1

-

10×10, 9×1

-

109×1

1st layer

Fully-connected

128

Conv_2D

16, 3×3, 2×2

Conv_1D

16, 3×1, 2×1

2nd layer

Fully-connected

128

Conv_2D

32, 3×3, 2×2

Conv_1D

32, 3×1, 2×1

3rd layer

Fully-connected

128

Fully-connected

128

Fully-connected

128

4th layer

Fully-connected

128

Fully-connected

128

Fully-connected

128

5th layer

Fully-connected

128

Fully-connected

128

Fully-connected

128

Output

-

3×1

-

3×1

-

3×1