Learning and retrieval in attractor neural networks above saturation
Learning and retrieval in attractor neural networks above saturation
复制标题
饱和以上吸引子神经网络的学习和检索
DOI：
10.1088/0305-4470/24/3/030
复制
发表时间：
1991
期刊：
影响因子：
--
通讯作者：
H. Gutfreund
中科院分区：
文献类型：
--
作者：
M. Griniasty;H. Gutfreund
作者研究了基态能量为正时参数范围内的神经网络；即，当学习算法无法找到满足所有所需约束的突触矩阵时。特别是，他们计算了该区域中许多算法获得的局部稳定性的典型分布函数。这些函数用于研究由吸引盆地大小反映的检索特性。这是在稀疏连接的网络中通过分析完成的，在完全连接的网络中通过数值完成的。主要结论是，吸引子神经网络的检索行为可以通过超过饱和度的学习来改善。
The authors investigate neural networks in the range of parameters when the ground-state energy is positive; namely, when a synaptic matrix which satisfies all the desired constraints cannot be found by the learning algorithm. In particular, they calculate the typical distribution functions of local stabilities obtained for a number of algorithms in this region. These functions are used to investigate the retrieval properties as reflected by the size of the basins of attraction. This is done analytically in sparsely connected networks, and numerically in fully connected networks. The main conclusion is that the retrieval behaviour of attractor neural networks can be improved by learning above saturation.