Skip to main content
SpringerPlus

Table 2 Selected parameters for training the network

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

Back to article page