The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to train a network from scratch. On the other hand, the training of custom and lighter CNNs requires expertise, in the from-scratch case, and or high-end resources, as in the case of hardware-aware neural architecture search (HW NAS), limiting access to the technology by non-habitual NN developers. For this reason, we present ColabNAS, an affordable HW NAS technique for producing lightweight task-specific CNNs. Its novel derivative-free search strategy, inspired by Occam's razor, allows to obtain state-of-the-art results on the Visual Wake Word dataset, a standard TinyML benchmark, in just 3.1 GPU hours using free online GPU services such as Google Colaboratory and Kaggle Kernel.

翻译：当前从在大规模数据集上训练的卷积神经网络（CNN）进行迁移学习的趋势，在目标应用为具有足够数据以从头训练网络的定制化且有限范围的问题时，可能显得过度。另一方面，从头训练定制化且更轻量的CNN需要专业知识，以及高端资源（如硬件感知神经架构搜索（HW NAS）的情况），这限制了非习惯性NN开发者对该技术的访问。为此，我们提出ColabNAS，一种经济实惠的HW NAS技术，用于生成轻量级特定任务CNN。其受奥卡姆剃刀启发的无导数新型搜索策略，仅需3.1 GPU小时即可在标准TinyML基准Visual Wake Word数据集上获得最先进结果，且可借助Google Colaboratory和Kaggle Kernel等免费在线GPU服务实现。