论文标题
为什么我们要在神经网络中添加早期出口？
Why should we add early exits to neural networks?
论文作者
论文摘要
深度神经网络通常被设计为一组可区分的层，其中仅在运行完整堆栈后才获得预测。最近，一些贡献提出了拟议的技术，以赋予网络早期退出，从而可以在堆栈的中间点获得预测。这些多输出网络具有许多优点，包括：（i）推理时间的显着减少，（ii）降低过度拟合和消失梯度的趋势，以及（iii）在多层计算平台上分布的能力。此外，它们连接到更广泛的生物学合理性和分层认知推理的主题。在本文中，我们通过以统一的方式描述这些架构可以在时间约束的场景中设计，培训和实际部署的方式来对这个神经网络家族进行全面介绍。只要与之相关的一些开放研究问题，我们还将在5G和雾计算环境中进行深入描述他们的应用程序方案。
Deep neural networks are generally designed as a stack of differentiable layers, in which a prediction is obtained only after running the full stack. Recently, some contributions have proposed techniques to endow the networks with early exits, allowing to obtain predictions at intermediate points of the stack. These multi-output networks have a number of advantages, including: (i) significant reductions of the inference time, (ii) reduced tendency to overfitting and vanishing gradients, and (iii) capability of being distributed over multi-tier computation platforms. In addition, they connect to the wider themes of biological plausibility and layered cognitive reasoning. In this paper, we provide a comprehensive introduction to this family of neural networks, by describing in a unified fashion the way these architectures can be designed, trained, and actually deployed in time-constrained scenarios. We also describe in-depth their application scenarios in 5G and Fog computing environments, as long as some of the open research questions connected to them.
