Reducing computations in incremental learning for feedforward neural network with long-term memory
Reducing computations in incremental learning for feedforward neural network with long-term memory
复制标题
减少具有长期记忆的前馈神经网络增量学习的计算量
DOI：
10.1109/ijcnn.2001.938469
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
S. Abe
中科院分区：
文献类型：
--
作者：
M. Kobyashi;A. Zamani;S. Ozawa;S. Abe
当神经网络被增量训练时，以前训练的输入-输出关系往往会因为学习新的训练数据而崩溃。这种现象被称为“干扰”。为了抑制干扰，我们提出了一种增量学习系统（称为RAN-LTM），其中长期记忆（LTM）被引入到资源分配网络（RAN）。由于RAN-LTM不仅需要训练新数据，而且需要训练一些LTM数据来抑制干扰，如果检索许多LTM数据，则需要大量计算。因此，在RAN-LTM中设计适当的LTM数据生成和检索程序非常重要。在本文中，这些程序在以前版本的RAN-LTM的改进。在仿真实验中，将改进的RAN-LTM应用于一维函数的逼近，并与RAN和原RAN-LTM进行比较，评估其逼近误差和训练速度。
When neural networks are trained incrementally, input-output relationships that are trained formerly tend to be collapsed by the learning of new training data. This phenomenon is called "interference". To suppress the interference, we have proposed an incremental learning system (called RAN-LTM), in which long-term memory (LTM) is introduced into a resource allocating network (RAN). Since RAN-LTM needs to train not only new data but also some LTM data to suppress the interference, if many LTM data are retrieved large computations are required. Therefore, it is important to design appropriate procedures for producing and retrieving LTM data in RAN-LTM. In the paper, these procedures in the previous version of RAN-LTM are improved. In simulations, the improved RAN-LTM is applied to the approximation of a one-dimensional function, and the approximation error and the training speed are evaluated as compared with RAN and the previous RAN-LTM.
使用模块化神经网络检测未知环境的气体泄漏声音。
DOI：
--
发表时间：
2004
期刊：
Neurocomputing 62C
影响因子：
--
作者：
Manabu KOTANI;Seiichi OZAWA
通讯作者：
Seiichi OZAWA