支持近似乘子的进化神经结构搜索
Evolutionary Neural Architecture Search Supporting Approximate Multipliers
摘要：
自动神经结构搜索（NAS）方法越来越受到人们的关注。它们通常用于为各种具有挑战性的数据集提供高质量的神经网络架构，并减少设计人员的工作量。当目标不仅是最小化网络误差，而且是最小化推理阶段的参数（权重）或功耗的数量时，利用多目标进化算法的NAS方法特别有用。提出了一种基于笛卡尔遗传编程的多目标进化卷积神经网络（CNN）的NAS方法。该方法允许在CNN中使用近似运算以降低目标硬件实现的功耗。在NAS过程中，一个合适的CNN架构与近似乘法器一起演进，以提供准确性、网络大小和功耗之间的最佳权衡。从近似乘数库中自动选择最合适的近似乘数。在CIFAR-10基准问题上，将进化的CNN与具有类似复杂性的常见人类创建的CNN进行比较。
英文摘要：
There is a growing interest in automated neural architecture search (NAS) methods. They are employed to routinely deliver high-quality neural network architectures for various challenging data sets and reduce the designer's effort. The NAS methods utilizing multi-objective evolutionary algorithms are especially useful when the objective is not only to minimize the network error but also to minimize the number of parameters (weights) or power consumption of the inference phase. We propose a multi-objective NAS method based on Cartesian genetic programming for evolving convolutional neural networks (CNN). The method allows approximate operations to be used in CNNs to reduce the power consumption of a target hardware implementation. During the NAS process, a suitable CNN architecture is evolved together with approximate multipliers to deliver the best trade-offs between the accuracy, network size, and power consumption. The most suitable approximate multipliers are automatically selected from a library of approximate multipliers. Evolved CNNs are compared with common human-created CNNs of a similar complexity on the CIFAR-10 benchmark problem.
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。
