论文标题
UDC：可压缩蒂米尔模型的统一DNA
UDC: Unified DNAS for Compressible TinyML Models
论文作者
论文摘要
由于设备内存能力有限，因此在低成本IoT硬件上部署TinyML模型非常具有挑战性。神经处理单元（NPU）硬件通过使用模型压缩来利用权重量化和稀疏性来解决内存挑战，以适合相同的足迹中的更多参数。但是，设计可压缩的神经网络（NNS）是具有挑战性的，因为它扩大了我们必须进行平衡权衡的设计空间。本文展示了可压缩（UDC）NNS的统一DNA，该DNA探索了一个较大的搜索空间，以生成最新的NPU可压缩NN。 ImageNet结果显示，UDC网络的价格高达$ 3.35 \ times $ $较小（ISO-ACRCURACY），或者比以前的工作更准确（ISO模型尺寸）6.25％。
Deploying TinyML models on low-cost IoT hardware is very challenging, due to limited device memory capacity. Neural processing unit (NPU) hardware address the memory challenge by using model compression to exploit weight quantization and sparsity to fit more parameters in the same footprint. However, designing compressible neural networks (NNs) is challenging, as it expands the design space across which we must make balanced trade-offs. This paper demonstrates Unified DNAS for Compressible (UDC) NNs, which explores a large search space to generate state-of-the-art compressible NNs for NPU. ImageNet results show UDC networks are up to $3.35\times$ smaller (iso-accuracy) or 6.25% more accurate (iso-model size) than previous work.
