Selection Criteria for Neuromanifolds of Stochastic Dynamics

Selection Criteria for Neuromanifolds of Stochastic Dynamics
复制标题

随机动力学神经流形的选择标准

DOI:
--
复制
发表时间:
2013
期刊:
影响因子:
--
通讯作者:
Johannes Rauh
Johannes Rauh
中科院分区:
--
文献类型:
--
作者:
N. Ay;Guido Montúfar;Johannes Rauh

文献摘要

被引文献

相似文献

我们提出了定义神经流形的方法-随机矩阵的模型-与目标函数的最大化兼容,例如强化学习理论中的预期奖励。我们的方法是基于信息几何,旨在减少模型参数的数量,希望改善梯度学习过程。
We present ways of defining neuromanifolds – models of stochastic matrices – that are compatible with the maximization of an objective function such as the expected reward in reinforcement learning theory. Our approach is based on information geometry and aims to reduce the number of model parameters with the hope to improve gradient learning processes.