论文标题
贝叶斯的一种贝叶斯的方法，用于重新传播神经网中重量的初始化，并应用于角色识别
A Bayesian approach for initialization of weights in backpropagation neural net with application to character recognition
论文作者
论文摘要
神经网络的训练算法的收敛速率受重量初始化的严重影响。在本文中，介绍了一种用于返回神经网中重量初始化的原始算法，并应用于角色识别。初始化方法主要基于卡尔曼过滤器的自定义化，将其转化为贝叶斯统计术语。在这种情况下，使用了一种计量方法，将权重作为由相互依赖的正常随机变量建模的测量值。通过报告和讨论模拟试验的结果来证明算法性能。将结果与随机权重初始化和其他方法进行比较。提出的方法显示了反向传播训练算法的收敛速率提高。
Convergence rate of training algorithms for neural networks is heavily affected by initialization of weights. In this paper, an original algorithm for initialization of weights in backpropagation neural net is presented with application to character recognition. The initialization method is mainly based on a customization of the Kalman filter, translating it into Bayesian statistics terms. A metrological approach is used in this context considering weights as measurements modeled by mutually dependent normal random variables. The algorithm performance is demonstrated by reporting and discussing results of simulation trials. Results are compared with random weights initialization and other methods. The proposed method shows an improved convergence rate for the backpropagation training algorithm.
