From: Urdu Nasta’liq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks
Parameters
Values
Input block size
4 × 1
Hidden bolck size
4 × 2
Subsample sizes
6 and 20
Hidden sizes
2, 10, 50
Learn rate
1 × 10−4
Momentum
0.9
Total network weight
551,405