UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units

Igor Fedorov · Ramon Matas · Hokchhay Tann · Chuteng Zhou · Matthew Mattina · Paul Whatmough

Hall J #200

Keywords: [ NPU ] [ NAS ] [ compression ]

[ Abstract ]
[ Paper [ Poster [ OpenReview
Thu 1 Dec 2 p.m. PST — 4 p.m. PST


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.

Chat is not available.