Adaptive Space Reconstruction and Generalization on Hidden Layer in Neural Networks with Local Inputs
Adaptive Space Reconstruction and Generalization on Hidden Layer in Neural Networks with Local Inputs
复制标题
局部输入神经网络隐藏层的自适应空间重构和泛化
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
Koji Ito
中科院分区：
文献类型：
--
作者：
社団法人 電子情報通信学会;K. Shibata;Koji Ito
我们的生物通过整合局部感觉信号（如视觉感觉信号）在大脑中表达全局信息。本文研究了具有局部输入的分层神经网络在学习后隐层的状态。一些字符变得清晰如下。(1)If训练信号在空间上逐渐变化，隐层变为表示空间信息。（2）这种倾向在较高的隐藏层中更强。(3)If存在冗余的隐层神经元，它们完全代表全局信息，而每个隐层神经元由于初始连接权重而保持初始（CID：13）波动。(4)If在两个输入区域的训练信号之间没有相关性，一个区域的学习变得不影响另一个区域的学习。（5）然而，隐藏神经元不会变成仅代表一个区域的信息。根据这些结果，可以认为隐藏层通过强化学习[1]来表示空间信息的原因如下。状态评估值随着到达目标的时间逐渐变化，而对于具有相同评估值的状态，运动应该逐渐变化。
Our living creatures represent global information in their brain by integrating local sensory signals such as visual sensory signals. In this paper, the state of hidden layer in a layered neural network with local inputs after learning was observed for some cases. Some characters became clear as follows. (1)If the training signal changes gradually in space, the hidden layer becomes to represent the spatial information. (2)This tendency is stronger in the higher hidden layer. (3)If there are redundant hidden neurons, they represent the global information totally, while each of them keeps the initial (cid:13)uctuation due to the initial connection weights. (4)If there is no correlation between the training signal of two input region, the learning of one region becomes not to in(cid:13)uence to the learning of the other region. (5)However, the hidden neurons does not become to represent the information for only one region. From these results, the reason why the hidden layer becomes to represent spatial information by reinforcement learning[1] can be thought as follows. The state evaluation value changes gradually according to the time to the goal, while motion should change gradually for the states with the same evaluation value.