Table 6 DFNN model performance in Q2 with K-fold.

From: Path-based evaluation of deep learning models for solving inverse kinematics in a revolute-prismatic robot

Configuration

Architecture (hidden layers × units)

Batch size

L2 regularization

Epoch

Validation loss

Single-output (\(\:\theta\:\))

5 × 128

32

0.0005

150

0.0208

Single-output (\(\:d\))

0.3953

Dual-output (\(\:\theta\:,\:d\))

3 × 128

0.00415

Back to article page