论文标题
卷积神经生成编码：缩放预测编码为自然图像
Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images
论文作者
论文摘要
在这项工作中，我们开发了卷积神经生成编码（CORV-NGC），这是对基于卷积/反卷积计算的情况进行预测性编码的概括。具体而言，我们会具体实施一种灵活的神经生物学动机算法，该算法逐渐完善了潜在状态特征图，以动态形成更准确的自然图像的内部表示/重建模型。在复杂的数据集（例如Color-Mnist，Cifar-10和Street House View编号（SVHN））上评估了所得的感官处理系统的性能。我们研究了大脑启发模型对重建和图像降解任务的有效性，并发现它具有通过错误反向传播培训的卷积自动编码系统竞争，并且相对于分发的重建（包括完整的90k Cinic-10测试集），并胜过它们的表现。
In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible neurobiologically-motivated algorithm that progressively refines latent state feature maps in order to dynamically form a more accurate internal representation/reconstruction model of natural images. The performance of the resulting sensory processing system is evaluated on complex datasets such as Color-MNIST, CIFAR-10, and Street House View Numbers (SVHN). We study the effectiveness of our brain-inspired model on the tasks of reconstruction and image denoising and find that it is competitive with convolutional auto-encoding systems trained by backpropagation of errors and outperforms them with respect to out-of-distribution reconstruction (including the full 90k CINIC-10 test set).
