Efficient deep learning inference requires algorithm and hardware codesign to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom from the neural architecture design makes the design space much larger: it is not only about designing the hardware architecture but also codesigning the neural architecture to fit the hardware architecture. It is difficult for human engineers to exhaust the design space by heuristics. We propose design automation techniques for architecting efficient neural networks given a target hardware platform. We investigate automatically designing specialized and fast models, auto channel pruning, and auto mixed-precision quantization. We demonstrate that such learning-based, automated design achieves superior performance and efficiency than the rule-based human design. Moreover, we shorten the design cycle by 200× than previous work, so that we can afford to design specialized neural network models for different hardware platforms.

中文翻译：

---

用于构建高效和专业神经网络的 AutoML

高效的深度学习推理需要算法和硬件协同设计来实现专业化：我们通常需要改变算法以减少内存占用并提高能效。然而，神经架构设计的额外自由度使得设计空间更大：它不仅是设计硬件架构，还包括对神经架构进行代码设计以适应硬件架构。人类工程师很难通过启发式方法耗尽设计空间。我们提出了设计自动化技术，用于在给定目标硬件平台的情况下构建高效的神经网络。我们研究了自动设计专业和快速模型、自动通道修剪和自动混合精度量化。我们证明，这种基于学习的，与基于规则的人工设计相比，自动化设计实现了卓越的性能和效率。此外，我们将设计周期比之前的工作缩短了 200 倍，因此我们能够为不同的硬件平台设计专门的神经网络模型。