进化卷积：可微分模式生成网络
Convolution by Evolution: Differentiable Pattern Producing Networks
摘要：
在这项工作中，我们介绍了一个可微版本的组合模式生产网络，称为DPPN。与标准CPPN不同，DPPN的拓扑是演进的，但权重是学习的。拉马克算法结合了进化和学习，产生DPPN来重建图像。我们的主要结果是，DPPN可以进化/训练，将去噪自动编码器的权重从157684压缩到大约200个参数，同时实现与具有两个数量级以上参数的完全连接网络相当的重建精度。DPPN的正则化能力允许它重新发现（近似）嵌入在完全连接架构中的卷积网络架构。这种卷积架构是许多计算机视觉应用的当前技术水平，因此DPPN能够发现这种结构而不是必须通过设计来构建它是令人满意的。DPPN在MNIST上训练后在Omniglot数据集上测试时表现出更好的泛化能力，而不是直接编码的全连接自动编码器。因此，DPPN是整合学习和进化的新框架。
英文摘要：
In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines evolution and learning, produces DPPNs to reconstruct an image. Our main result is that DPPNs can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters, while achieving a reconstruction accuracy comparable to a fully connected network with more than two orders of magnitude more parameters. The regularization ability of the DPPN allows it to rediscover (approximate) convolutional network architectures embedded within a fully connected architecture. Such convolutional architectures are the current state of the art for many computer vision applications, so it is satisfying that DPPNs are capable of discovering this structure rather than having to build it in by design. DPPNs exhibit better generalization when tested on the Omniglot dataset after being trained on MNIST, than directly encoded fully connected autoencoders. DPPNs are therefore a new framework for integrating learning and evolution.
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。
