SELF-ORGANIZING NEURAL NETWORK THAT DISCOVERS SURFACES IN RANDOM-DOT STEREOGRAMS
SELF-ORGANIZING NEURAL NETWORK THAT DISCOVERS SURFACES IN RANDOM-DOT STEREOGRAMS
复制标题
DOI：
10.1038/355161a0
复制
发表时间：
1992-01-09
期刊：
影响因子：
64.8
通讯作者：
HINTON, GE
中科院分区：
文献类型：
--
作者：
BECKER, S;HINTON, GE
反向传播学习的标准形式1作为感知学习的模型是不可信的，因为它需要外部教师来指定网络的期望输出。我们展示了外部教师如何可以被内部衍生的教学信号所取代。这些信号是通过假设感知输入的不同部分在外部世界中具有共同的原因而产生的。观察知觉输入中分离但相关的部分的小模块通过努力产生彼此一致的输出来发现这些共同的原因（图1a）。这些模块可以查看不同的模态（例如视觉和触摸），或者在不同时间查看相同的模态（例如，旋转三维对象的连续二维视图），或者甚至查看同一图像的空间相邻部分。我们的模拟表明，当我们的学习过程应用于二维图像的相邻块时，它允许没有第三维先验知识的神经网络发现曲面随机点立体图中的深度。
THE standard form of back-propagation learning 1 is implausible as a model of perceptual learning because it requires an external teacher to specify the desired output of the network. We show how the external teacher can be replaced by internally derived teaching signals. These signals are generated by using the assumption that different parts of the perceptual input have common causes in the external world. Small modules that look at separate but related parts of the perceptual input discover these common causes by striving to produce outputs that agree with each other (Fig. 1a). The modules may look at different modalities (such as vision and touch), or the same modality at different times (for example, the consecutive two-dimensional views of a rotating three-dimensional object), or even spatially adjacent parts of the same image. Our simulations show that when our learning procedure is applied to adjacent patches of two-dimensional images, it allows a neural network that has no prior knowledge of the third dimension to discover depth in random dot stereograms of curved surfaces.