`

Timezone: »

 
MLPerf Tiny Benchmark
Colby Banbury · Vijay Janapa Reddi · Peter Torelli · Nat Jeffries · Csaba Kiraly · Jeremy Holleman · Pietro Montino · David Kanter · Pete Warden · Danilo Pau · Urmish Thakker · antonio torrini · jay cordaro · Giuseppe Di Guglielmo · Javier Duarte · Honson Tran · Nhan Tran · niu wenxu · xu xuesong

Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark for these systems. To meet this need, we present MLPerf Tiny, the first industry-standard benchmark suite for ultra-low-power tiny machine learning systems. The benchmark suite is the collaborative effort of more than 50 organizations from industry and academia and reflects the needs of the community. MLPerf Tiny measures the accuracy, latency, and energy of machine learning inference to properly evaluate the tradeoffs between systems. Additionally, MLPerf Tiny implements a modular design that enables benchmark submitters to show the benefits of their product, regardless of where it falls on the ML deployment stack, in a fair and reproducible manner. The suite features four benchmarks: keyword spotting, visual wake words, image classification, and anomaly detection.

Author Information

Colby Banbury (Harvard University)
Vijay Janapa Reddi (Harvard University)
Peter Torelli
Nat Jeffries
Csaba Kiraly
Jeremy Holleman (University of North Carolina, Charlotte)
Pietro Montino
David Kanter (MLCommons)
Pete Warden (Google)
Danilo Pau (STMicroelectronics)

One year before graduating from the Polytechnic University of Milan in 1992, Danilo PAU joined STMicroelectronics, where he worked on HDMAC and MPEG2 video memory reduction, video coding, embedded graphics, and computer vision. Today, his work focuses on developing solutions for deep learning tools and applications. Since 2019 Danilo is an IEEE Fellow, serves as Industry Ambassador coordinator for IEEE Region 8 South Europe and Member of the Machine Learning, Deep Learning and AI in the CE (MDA) Technical Stream Committee IEEE Consumer Electronics Society (CESoc). With over 80 patents, 94 publications, 113 MPEG authored documents and more than 31 invited talks/seminars at various worldwide Universities and Conferences, Danilo's favorite activity remains mentoring undergraduate students, MSc engineers and PhD students from various universities in Italy, US, France and India.

Urmish Thakker (Arm ML Research Lab)
antonio torrini
jay cordaro
Giuseppe Di Guglielmo (Columbia University)
Javier Duarte (University of California San Diego)
Honson Tran
Nhan Tran (Fermilab)
niu wenxu
xu xuesong

More from the Same Authors