A fast incremental learning algorithm of RBF networks with long-term memory
A fast incremental learning algorithm of RBF networks with long-term memory
复制标题
一种具有长期记忆的RBF网络快速增量学习算法
DOI：
10.1109/ijcnn.2003.1223305
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Shigeo Abe
中科院分区：
文献类型：
--
作者：
Keisuke Okamoto;Seiichi Ozawa;Shigeo Abe
为了避免增量学习中的灾难性干扰，我们提出了长期记忆资源分配网络（RAN-LTM）。在ranl - ltm算法中，不仅对新的训练样本进行训练，而且对存储在长期记忆中的部分记忆项也采用梯度下降算法进行训练，该算法速度慢，容易陷入局部极小值。为了解决这些问题，我们提出了一种快速增量学习算法RAN-LTM，该算法不训练中心，而是根据输出误差选择中心。该模型不需要太多的记忆容量，并且实现了鲁棒的增量学习能力。为了验证RAN/spl I.bar/LTM的这些特性，我们将其应用于两个函数逼近问题：一维函数逼近和Mackey-Glass时间序列的预测。实验结果表明，除非长时间进行增量学习，否则所提出的RAN-LTM可以在没有大内存的情况下快速准确地学习。
To avoid the catastrophic interference in incremental learning, we have proposed resource allocating network with long term memory (RAN-LTM). In RAN-LTM, not only a new training sample but also some memory items stored in long-term memory are trained based on a gradient descent algorithm is usually slow and can be easily fallen into local minima. To solve these problems, we propose a fast incremental learning algorithm of RAN-LTM, in which its centers are not trained but selected based on output errors. This model does not need so much memory capacity and it is also realizes robust incremental learning ability. To verify these characteristics of RAN/spl I.bar/LTM, we apply it to two function approximation problems: one-dimensional function approximation and prediction of Mackey-Glass time series. From the experimental results, it is verified that the proposed RAN-LTM can learn fast and accurately without large main memory unless incremental learning is conducted over long period of time.