面向新朝向物体泛化的涌现神经网络机制
Emergent Neural Network Mechanisms for Generalization to Objects in Novel Orientations
AI总结:
该研究探究DNNs对训练分布外朝向物体的泛化能力,发现其可通过熟悉物体的朝向不变性实现,且与调谐共同特征的神经元有关,揭示类脑泛化机制。
摘要:
深度神经网络(DNNs)对训练数据分布外朝向的物体识别能力尚未得到充分理解。我们提供证据表明,DNNs能通过从多视角熟悉物体中获得的朝向不变性,实现对新朝向物体的泛化。当用数量递增的熟悉物体训练DNN时,该能力会增强,但仅针对熟悉物体朝向的二维旋转相关朝向。我们还表明,这种泛化能力通过对熟悉与新物体间共同特征调谐的神经元实现,这些结果揭示了类脑的泛化神经机制。
英文摘要:
The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the distribution of the training data is not well understood. We present evidence that DNNs are capable of generalizing to objects in novel orientations by disseminating orientation-invariance obtained from familiar objects seen from many viewpoints. This capability strengthens when training the DNN with an increasing number of familiar objects, but only in orientations that involve 2D rotations of familiar orientations. We show that this dissemination is achieved via neurons tuned to common features between familiar and unfamiliar objects. These results implicate brain-like neural mechanisms for generalization.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。