paper-with-me

Papers

Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow

2024-08-05 · Philip Wiese, Gamze İslamoğlu, Moritz Scherer, Luka Macan, Victor J. B. Jung, Alessio Burrello, Francesco Conti, Luca Benini

One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address this by leveraging a heterogeneous architectural template coupling RISC-V processors with hardwired accelerators supported by an automated deployment flow. We demonstrate Attention-based models in a tinyML power envelope with an octa-core cluster coupled with an accelerator for quantized Attention. Our deployment flow enables end-to-end 8-bit Transformer inference, achieving leading-edge energy efficiency and throughput of 2960 GOp/J and 154 GOp/s (0.65 V, 22 nm FD-SOI technology).

📄 PDF Abstract BibTeX arXiv:2408.02473

Code (1)

pulp-platform/deeploy 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation

2025-02-18 · Emil Njor, Colby Banbury, Xenofon Fafoutis

Tiny machine learning (TinyML) promises to revolutionize fields such as healthcare, environmental monitoring, and industrial maintenance by running machine learning models on low-power embedded systems. However, the comp…

AutoMLNeural Architecture Search

MultiCore+TPU Accelerated Multi-Modal TinyML for Livestock Behaviour Recognition

2025-04-10 · Qianxue Zhang, Eiman Kanjo

The advancement of technology has revolutionised the agricultural industry, transitioning it from labour-intensive farming practices to automated, AI-powered management systems. In recent years, more intelligent livestoc…

Activity Recognitionimage-classificationImage Classificationobject-detection+1

On-device Online Learning and Semantic Management of TinyML Systems

2024-05-13 · Haoyu Ren, Xue Li, Darko Anicic, Thomas A. Runkler

Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of TinyML, its practical implementation pre…

Audio Classificationimage-classificationImage ClassificationManagement+1

Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review

2023-11-20 · Minh Tri Lê, Pierre Wolinski, Julyan Arbel

The field of Tiny Machine Learning (TinyML) has gained significant attention due to its potential to enable intelligent applications on resource-constrained devices. This review provides an in-depth analysis of the advan…

Model CompressionQuantization

Edge Impulse: An MLOps Platform for Tiny Machine Learning

2022-11-02 · Shawn Hymel, Colby Banbury, Daniel Situnayake, Alex Elium 외

Edge Impulse is a cloud-based machine learning operations (MLOps) platform for developing embedded and edge ML (TinyML) systems that can be deployed to a wide range of hardware targets. Current TinyML workflows are plagu…