UDC: Unified DNAS for Compressible TinyML Models for Neural Processing UnitsDownload PDF

Published: 31 Oct 2022, Last Modified: 05 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: NAS, compression, NPU
Abstract: 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 3.35x smaller (iso-accuracy) or 6.25% more accurate (iso-model size) than previous work.
Supplementary Material: pdf
14 Replies