Learning recurrent neural models with minimal complexity from neural tuning

机译：通过神经调整以最小的复杂度学习循环神经模型

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

A learning algorithm for the estimation of the structure of nonlinear recurrent neural models from neural tuning data is presented. The proposed method combines support vector regression with additional constraints that result from a stability analysis of the dynamics of the fitted network model. The optimal solution can be determined from a single convex optimization problem that can be solved with semidefinite programming techniques. The method successfully estimates the feed-forward and the recurrent connectivity structure of neural field models using as data only examples of stable stationary solutions of the neural dynamics. The class of neural models that can be learned is quite general. The only a priori assumptions are the translation invariance and the smoothness of the feed-forward and recurrent spatial connectivity profile. The efficiency of the method is illustrated by comparing it with estimates based on radial basis function networks and support vector regression.

机译：提出了一种从神经调节数据估计非线性递归神经模型结构的学习算法。所提出的方法将支持向量回归与附加约束相结合，附加约束是由拟合网络模型的动力学稳定性分析得出的。可以从可以用半定编程技术解决的单个凸优化问题中确定最佳解决方案。该方法仅使用神经动力学的稳定平稳解的示例作为数据，成功地估计了神经场模型的前馈和递归连通性结构。可以学习的神经模型类别非常笼统。唯一的先验假设是平移不变性，前馈和递归空间连通性分布图的平滑度。通过将其与基于径向基函数网络和支持向量回归的估计值进行比较，说明了该方法的效率。

著录项

来源
《Annual Computational Neuroscience Meeting(CNS'02); 20020721-20020725; Chicago,IL; US》|2002年|P.277-283|共7页
会议地点 Chicago IL(US);Chicago IL(US)
作者
Martin A. Giese;
展开▼
作者单位

Department for Cognitive Neurology, Laboratory for Action Representation and Learning, University Clinic Tuebingen, Spemannstr. 34, D-72076 Tuebingen, Germany;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类系统科学;
关键词
recurrent neural network; support vector regression; dynamic stability;

机译：递归神经网络;支持向量回归;动态稳定性;

相似文献

外文文献
中文文献
专利

1. Learning recurrent neural models with minimal complexity from neural tuning data [J] . Martin A. Giese Neurocomputing . 2003,第Jun期

机译：从神经调整数据中以最小的复杂度学习循环神经模型
2. Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach [J] . Rumeng Li, Baotian Hu, Feifan Liu, JMIR Medical Informatics . 2019,第1期

机译：使用循环神经网络自动编码器增强的卷积神经网络模型检测电子病历中的出血事件：深度学习方法
3. Recurrent neural system with minimum complexity: A deep learning perspective [J] . Sun Xiaochuan, Li Tao, Li Yingqi, Neurocomputing . 2018,第JANa31期

机译：具有最小复杂度的递归神经系统：深度学习视角
4. Learning recurrent neural models with minimal complexity from neural tuning [C] . Martin A. Giese Computational neuroscience meeting . 2003

机译：从神经调整的复杂性最小的复杂性学习经常性神经模型
5. Recurrent neural network learning and neural network learning controller. [D] . Yan, Lilai. 1994

机译：递归神经网络学习和神经网络学习控制器。
6. The advantage of flexible neuronal tunings in neural network models for motor learning [O] . Ellisha N. Marongelli, Kurt A. Thoroughman 2013

机译：灵活的神经元调整在运动学习神经网络模型中的优势
7. Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach [O] . Rumeng Li, Baotian Hu, Feifan Liu, 2019

机译：用经常性神经网络自动化器增强卷积神经网络模型检测电子健康记录笔记中的出血事件：深度学习方法

Learning recurrent neural models with minimal complexity from neural tuning

摘要

著录项

相似文献

相关主题

期刊订阅