TL;DR本文提出了结合 BP 算法的 BDFA 算法,同时提出了反馈权重初始化方法和模式分析技术来维持训练稳定性和最小化计算成本。 实验结果表明,该方法在小数据集环境下表现优异。
Abstract
There were many algorithms to substitute the back-propagation (BP) in the
deep neural network (DNN) training. However, they could not become popular
because their training accuracy and the computational efficienc