Fast Teaching of Boltzmann Machines with Local Inhibition
Fast Teaching of Boltzmann Machines with Local Inhibition
复制标题
具有局部抑制的玻尔兹曼机的快速教学
DOI：
10.1007/978-94-009-0643-3_76
复制
发表时间：
1990
期刊：
影响因子：
--
通讯作者：
T. Osborn
中科院分区：
文献类型：
--
作者：
T. Osborn
通过补充输入到输出玻尔兹曼机的目标函数（而不是通过严格竞争）来对侧向抑制的局部集群进行软建模。这会挫败数据诱导内部表示的不必要的复杂性。此外，增量教学（整形）将新数据与先前学习的数据进行最少的再训练结合起来。尽管最大存储容量略有降低，但最终的学习率比标准模型好一个数量级以上。
Local clusters of lateral inhibition are modelledsoftlyby supplementing the objective function (rather than by strict competition) for the Input_to_Output Boltzmann machine.This frustrates unwanted complexity of the induced internal representation of data.Furthermore, incremental teaching (shaping) incorporates new data with minimal retraining of previously learned data.Consequent learning rates are well over an order of magnitude better than the standard models, although maximum storage capacity is marginally reduced.