Predictive coding has been proposed as a model of the hierarchical perceptual inference process performed in the cortex. However, results demonstrating that predictive coding is capable of performing the complex inference required to recognise objects in natural images have not previously been presented. This article proposes a hierarchical neural network based on predictive coding for performing visual object recognition. This network is applied to the tasks of categorising hand-written digits, identifying faces, and locating cars in images of street scenes. It is shown that image recognition can be performed with tolerance to position, illumination, size, partial occlusion, and within-category variation. The current results, therefore, provide the first practical demonstration that predictive coding (at least the particular implementation of predictive coding used here; the PC/BC-DIM algorithm) is capable of performing accurate visual object recognition.

中文翻译：

---

自然图像中对象识别的分层预测编码模型。

预测编码已被提议作为在皮层中执行的分层感知推理过程的模型。然而，之前尚未提出证明预测编码能够执行识别自然图像中的对象所需的复杂推理的结果。本文提出了一种基于预测编码的分层神经网络，用于执行视觉对象识别。该网络适用于对手写数字进行分类、识别人脸以及在街道场景图像中定位汽车等任务。结果表明，图像识别可以在容忍位置、照明、尺寸、部分遮挡和类别内变化的情况下进行。因此，当前的结果提供了第一个实际证明，即预测编码（至少是这里使用的预测编码的特定实现；PC/BC-DIM 算法）能够执行准确的视觉对象识别。