机译:在错误的反向传播下学习分段记忆递归神经网络中的长期依赖性
Faculty of Electrical Engineering and Information Technology,Cognitive Systems Group,Otto von Guericke University Magdeburg and Center for Behavioral Brain Science,Universitaetsplatz 2,39106 Magdeburg,Germany,School of Life Science and Facility Management,Institute of Applied Simulation,Zurich University of Applied Sciences,Einsiedlerstrasse 31a,8820 Waedenswil,Switzerland;
Faculty of Electrical Engineering and Information Technology,Cognitive Systems Group,Otto von Guericke University Magdeburg and Center for Behavioral Brain Science,Universitaetsplatz 2,39106 Magdeburg,Germany;
Faculty of Computer Science,Institute of Neural Information Processing,Ulm University,89069 Ulm,Germany;
Faculty of Electrical Engineering and Information Technology,Cognitive Systems Group,Otto von Guericke University Magdeburg and Center for Behavioral Brain Science,Universitaetsplatz 2,39106 Magdeburg,Germany;
Recurrent neural networks; Segmented-memory recurrent neural; network; Vanishing gradient problem; Long-term dependencies; Unsupervised pre-training;
机译:使用递归神经网络学习长期依赖
机译:学习NARX递归神经网络中的长期依赖关系
机译:递归神经网络中的稳定动态反向传播学习
机译:学习分段记忆递归神经网络中的长期依赖性
机译:递归神经网络学习和神经网络学习控制器。
机译:在二进制状态网络中通过流水线式截断错误反向传播进行硬件有效的在线学习
机译:学习NARX递归神经网络中的长期依赖关系