Becker S, Hinton G E
Department of Computer Science, University of Toronto, Canada.
Nature. 1992 Jan 9;355(6356):161-3. doi: 10.1038/355161a0.
The standard form of back-propagation learning 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. 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 discovery depth in random dot stereograms of curved surfaces.
反向传播学习的标准形式作为一种感知学习模型是不合理的，因为它需要外部教师来指定网络的期望输出。我们展示了如何用内部衍生的教学信号来取代外部教师。这些信号是通过假设感知输入的不同部分在外部世界有共同的原因而产生的。观察感知输入中不同但相关部分的小模块通过努力产生相互一致的输出，从而发现这些共同原因。这些模块可以观察不同的模态（如视觉和触觉），或者在不同时间观察相同的模态（例如，旋转的三维物体的连续二维视图），甚至观察同一图像在空间上相邻的部分。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小块时，它能让一个对第三维没有先验知识的神经网络在曲面随机点立体图中发现深度。
