https://blog.csdn.net/losteng/article/details/51058026
作者:Zack Zhou
链接:https://www.zhihu.com/question/35552071/answer/118775067
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
链接:https://www.zhihu.com/question/35552071/answer/118775067
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
两种典型的增量式神经网络模型,一种是基于在线学习的参数更新模型,如增量式BP算法。另一种基于增加隐藏层神经元的结构更新模型,如基于资源分配网络的RBF模型、增量式SVM及适应拓扑结构的增量式神经网络模型(OANN)。
参考文献:
卜范玉, et al. (2015). "支持增量式更新的大数据特征学习模型." 计算机工程与应用(12).
Dong, X., et al. (2008). Circuit and microarchitecture evaluation of 3D stacking magnetic RAM (MRAM) as a universal memory replacement. Design Automation Conference, 2008. DAC 2008. 45th ACM/IEEE, IEEE.
Wu, X., et al. (2009). Power and performance of read-write aware hybrid caches with non-volatile memories. 2009 Design, Automation & Test in Europe Conference & Exhibition, IEEE.
参考文献:
卜范玉, et al. (2015). "支持增量式更新的大数据特征学习模型." 计算机工程与应用(12).
Dong, X., et al. (2008). Circuit and microarchitecture evaluation of 3D stacking magnetic RAM (MRAM) as a universal memory replacement. Design Automation Conference, 2008. DAC 2008. 45th ACM/IEEE, IEEE.
Wu, X., et al. (2009). Power and performance of read-write aware hybrid caches with non-volatile memories. 2009 Design, Automation & Test in Europe Conference & Exhibition, IEEE.