Extracting information in a graded manner from a neural-network system with continuous attractors
Extracting information in a graded manner from a neural-network system with continuous attractors
复制标题
从具有连续吸引子的神经网络系统中以分级方式提取信息
DOI：
10.1109/ijcnn.2004.1381166
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
H. Okamoto
中科院分区：
文献类型：
--
作者：
Y. Tsuboshita;H. Okamoto
神经网络的记忆检索已经被描述为具有离散吸引子的动力系统。然而，最近的神经生理学研究表明，在大脑中的信息提取更有可能被描述为连续吸引子。在这里，我们提出了一个神经网络系统，提供连续的吸引相对于网络状态表示的向量。吸引子模式持续依赖于初始模式;它也反映了嵌入模式。这表明，对于由初始状态编码的每个查询，我们的模型可以从网络中提取不同的信息。为了证明这些信息的有用性，我们的模型被应用到从文档中提取关键字。
Memory retrieval from neural networks has been described by dynamical systems with discrete attractors. However, recent neurophysiological studies suggest that information extraction in the brain is more likely to be described with continuous attractors. Here we put forward a neural-network system that provides continuous attractors with respect to the network state represented by a vector quantity. An attractor pattern continuously depends upon an initial pattern; it also reflects the embedded pattern. These suggest that, for each query encoded by an initial state, our model can extract different information from the network. To demonstrate the usefulness of this information, our model is applied to keyword extraction from a document.