Its learning rule is to use the steepest descent method, by back-propagation network to continuously adjust the weights and thresholds, so the network and the minimum sum of squared errors.
它的学习规则是使用最速下降法，通过反向传播来不断调整网络的权值和阈值，使网络的误差平方和最小。
Minimum sum algorithm is very simple and is easy for hardware implementation. But the decoding performance is degraded.
最小和算法具有简单、容易实现的特点，但使译码性能较大幅度地降低。
Minimum sum algorithm is very simple and is easy for hardware implementation. But the decoding performance is degraded.
最小和算法具有简单、容易实现的特点，但使译码性能较大幅度地降低。
应用推荐