arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.00945q-bio.NCcs.LGcs.NE
收藏

通过解剖学约束的深CNN从视网膜到皮层的早期视觉表征的统一理论

A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs

Department of Applied Physics Stanford(斯坦福大学应用物理系);Google Brain(谷歌大脑)

Jack Lindsey, Samuel A. Ocko, Surya Ganguli, Stephane Deny

摘要:

视觉系统是分层组织的,在连续的阶段中处理视觉信息。在视觉处理的第一阶段,神经表征变化很大:在视网膜的输出端,神经节细胞感受野(RF)表现出明显的拮抗性中心-环绕结构,而在初级视觉皮层,典型的RF被急剧调整到精确的方向。目前还没有统一的理论来解释这些层间表征的差异。在这里,使用一个在图像识别上训练的深度卷积神经网络作为视觉系统的模型,我们证明了这种表征的差异可以作为视网膜和皮层网络上不同神经资源约束的直接结果出现,并且我们找到了一个单一的模型,在视觉处理的适当阶段,两种几何形状自发地出现。关键的限制是视网膜输出处的神经元数量减少,这与视神经的解剖结构作为严格的瓶颈一致。第二,我们发现,对于简单的皮层网络,在视网膜输出的视觉表示出现非线性和有损特征检测器,而他们出现的线性和忠实的编码器的视觉场景更复杂的皮层。这一结果预测,小型脊椎动物的视网膜应该执行复杂的非线性计算,提取与行为直接相关的特征,而大型动物(如灵长类动物)的视网膜应该主要对视觉场景进行线性编码,并对更广泛的刺激做出反应。这些预测可以调和两种看似不相容的视网膜观点,即要么执行特征提取,要么对自然场景进行有效编码,因为所有脊椎动物都位于这两个目标之间的光谱上,这取决于分配给视觉系统的神经资源的程度。

英文摘要:

The visual system is hierarchically organized to process visual information in successive stages. Neural representations vary drastically across the first stages of visual processing: at the output of the retina, ganglion cell receptive fields (RFs) exhibit a clear antagonistic center-surround structure, whereas in the primary visual cortex, typical RFs are sharply tuned to a precise orientation. There is currently no unified theory explaining these differences in representations across layers. Here, using a deep convolutional neural network trained on image recognition as a model of the visual system, we show that such differences in representation can emerge as a direct consequence of different neural resource constraints on the retinal and cortical networks, and we find a single model from which both geometries spontaneously emerge at the appropriate stages of visual processing. The key constraint is a reduced number of neurons at the retinal output, consistent with the anatomy of the optic nerve as a stringent bottleneck. Second, we find that, for simple cortical networks, visual representations at the retinal output emerge as nonlinear and lossy feature detectors, whereas they emerge as linear and faithful encoders of the visual scene for more complex cortices. This result predicts that the retinas of small vertebrates should perform sophisticated nonlinear computations, extracting features directly relevant to behavior, whereas retinas of large animals such as primates should mostly encode the visual scene linearly and respond to a much broader range of stimuli. These predictions could reconcile the two seemingly incompatible views of the retina as either performing feature extraction or efficient coding of natural scenes, by suggesting that all vertebrates lie on a spectrum between these two objectives, depending on the degree of neural resources allocated to their visual system.

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。

↑