arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.04866cs.LGcs.AIcs.CV
收藏

深度声明网络:新的希望

Deep Declarative Networks: A New Hope

Australian National University(澳大利亚国立大学);Australian Centre for Robotic Vision(澳大利亚机器人视觉中心)

Stephen Gould, Richard Hartley, Dylan Campbell

摘要:

我们探索了一类新的端到端可学习模型,其中数据处理节点(或网络层)是根据所需的行为而不是显式的转发函数来定义的。具体来说,前向函数被隐式地定义为数学优化问题的解。与程序设计语言社区的命名法一致,我们将这些模型命名为深度声明网络。重要的是,我们证明了深度声明性网络的类别包含了当前的深度学习模型。此外,调用隐函数定理,我们展示了梯度如何通过许多声明定义的数据处理节点反向传播,从而实现端到端学习。我们展示了如何在流行的PyTorch深度学习软件库中实现这些声明性处理节点,允许声明性和命令性节点在同一网络中共存。我们还提供了大量的见解和说明性的例子声明节点,并展示了他们的应用程序的图像和点云分类任务。

英文摘要:

We explore a new class of end-to-end learnable models wherein data processing nodes (or network layers) are defined in terms of desired behavior rather than an explicit forward function. Specifically, the forward function is implicitly defined as the solution to a mathematical optimization problem. Consistent with nomenclature in the programming languages community, we name these models deep declarative networks. Importantly, we show that the class of deep declarative networks subsumes current deep learning models. Moreover, invoking the implicit function theorem, we show how gradients can be back-propagated through many declaratively defined data processing nodes thereby enabling end-to-end learning. We show how these declarative processing nodes can be implemented in the popular PyTorch deep learning software library allowing declarative and imperative nodes to co-exist within the same network. We also provide numerous insights and illustrative examples of declarative nodes and demonstrate their application for image and point cloud classification tasks.

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。

↑