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

Deploying TinyML models on low-cost IoT hardware is very challenging, due to limited device memory capacity...

Share this article

Each week Tenstorrent will be highlighting a paper that has inspired our product development.

UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units by Igot Fedorov, Ramon Matas, Hokchhay Tann, Chuteng Zhou, Matthew Mattina, Paul Watmough.

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× smaller (iso-accuracy) or 6.25% more accurate (iso-model size) than previous work.

Read the full white paper here.

Other articles

Tenstorrent closes $693M+ of Series D funding led by Samsung Securities and AFW Partners

Santa Clara, CA: Tenstorrent is announcing that it has closed over $693M in its Series D funding round at a pre-money valuation of $2B.

Community Highlight: Tenstorrent Wormhole Series Part 2: Which disabled rows?

An in depth look at Tenstorrent Wormhole, originally posted on corsix.org

AI Software Startup Moreh Partners with AI Semiconductor Company Tenstorrent to Challenge NVIDIA in AI Data Center Market

Joint R&D of AI data center solutions by integrating tenstorrent's semiconductors with Moreh's software; Targeting NVIDIA dominant datacenter market with top-notch performance solutions