Stringer Simon M, Rolls Edmund T
Oxford University, Centre for Computational Neuroscience, Department of Experimental Psychology, Oxford OX1 3UD, England.
Neural Comput. 2002 Nov;14(11):2585-96. doi: 10.1162/089976602760407982.
To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.
为了形成物体的视图不变表示，颞下皮质中的神经元可能会将物体的不同视图关联在一起，在自然观察条件下，这些视图往往在时间上紧密相连。在这个过程的神经网络模型中，可以通过使用带有短期时间记忆痕迹的联想学习规则来实现这一点。据推测，在一个视图内，神经元学习能够使它们在该视图的变化范围内进行泛化的表示。当三维（3D）物体在小角度（例如，高达30度）内旋转时，由于视角的变化，其表面特征会发生几何变形。在本文中，我们展示了痕迹学习如何通过开发特征在3D物体表面时所经历的变换的表示来解决深度旋转不变物体识别问题。此外，我们表明，在学习了3D物体上的特征随着物体深度旋转如何进行几何变换后，网络能够在由先前学习的特征的新组合构成的物体的通用视图内正确识别新颖的3D变体。这些结果在视觉系统的分层网络模型（VisNet）的模拟中得到了证明，该模拟表明它可以通过形成视角不变表示来开发对3D物体识别有用的表示，从而在通用视图内进行泛化。
