Neurobiology suggests the design of modular architectures for neural control
Neurobiology suggests the design of modular architectures for neural control
复制标题
神经生物学建议设计神经控制的模块化架构
DOI：
10.1109/iros.2000.894583
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
J. Urban
中科院分区：
文献类型：
--
作者：
J. Buessler;J. Urban
生物世界中模块化结构的存在强烈表明这种结构的训练实际上是可行的。它是神经网络应用发展的关键指标，特别是在机器人领域。事实上，单个网络只能有效地处理自变量很少的问题；为了解决更复杂的任务，需要组合多个网络。我们研究了学习技术，并表明使用特定形式的架构可以简化模块化结构的训练：允许组合多个神经网络的双向结构。 Kohonen 的用于机器人视觉传感任务的自组织图说明了该方法。
The existence of modular structures in the biological world strongly suggests that the training of this kind of structures is actually feasible. It is a key indication for the development of neural networks applications especially in the field of robotics. Indeed, a single network can only efficiently treat problems with few independent variables; the combining of several networks is necessary to address more complex tasks. We investigate learning techniques and show that using a particular form of architecture can ease the training of a modular structure: a bi-directional structure that allows combining several neural networks. The approach is illustrated with Kohonen's self-organizing maps for a robotic visual sensing task.