Application Aware, Life-Cycle Oriented Model-Hardware Co-Design Framework for Sustainable, Energy Efficient ML Systems

Informazioni relative al progetto

SustainML

ID dell’accordo di sovvenzione: 101070408

DOI

10.3030/101070408

Data della firma CE 20 Giugno 2022

Data di avvio 1 Ottobre 2022

Data di completamento 30 Giugno 2026

Finanziato da

• Digital, Industry and Space

Costo totale

€ 3 742 855,00

Contributo UE

€ 3 742 855,00

Coordinato da

PROYECTOS Y SISTEMAS DE MANTENIMIENTO SL
Spain

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (8)

Explainable AI for decision making - Initial

A set of working examples of more context-dependent explainable AIs that allow intelligent systems to express trade-offs relevant to the current task more effectively than current approaches. An online tutorial that explains our method to enable other AI researchers to use this type of human-computer collaboration approach.

Report on communication, exploitation and dissemination - M18

Report on communication, exploitation and dissemination

Hardware accelerator architecture report

Report on the detailed analysis of suitable cross-layer optimizations used to design low-power and energy-efficient hardware accelerator architectures.

Annual report on collaboration - Y1

Annual report on collaboration

Report on communication, exploitation and dissemination - Initial

Report on communication, exploitation and dissemination

Task modeling from user definition results - Initial

Report on ML task stage and parameter space exploration, node graph descriptions, and results in problem modeling from user descriptions.

Framework architecture, back-end, front-end design and release - Y1

Reports on the frame architecture design that integrates all software interfaces from WP1-WP4, and software release of the back-end and front-end of the framework.

Exploring new ML models Report

Report on new interactive visualization methods to assist experienced and inexperienced ML developers in better understanding the design space of available ML models and in particular their relationships, benefits, and resource costs.

Demonstrators, pilots, prototypes (1)

Carbon footprint based model optimization tool

Data Management Plan (2)

Data Management Plan - M18

Data Management Plan

Data Management Plan - Initial

Data Management Plan

Pubblicazioni

Other (1)

Adaptive Conformal Regression with Jackknife+ Rescaled Scores

Autori: Deutschmann, Nicolas; Rigotti, Mattia; Martinez, Maria Rodriguez
Pubblicato in: 2023, ISSN 0000-0000
Editore: Transactions on Machine Learning Research, TMLR 2024
DOI: 10.48550/arxiv.2305.19901

Peer reviewed articles (7)

Mixed selectivity: Cellular computations for complexity

Autori: KM Tye, EK Miller, FH Taschbach, MK Benna, M Rigotti, S Fusi
Pubblicato in: NEURON, 2024, ISSN 1097-4199
Editore: NEURON
DOI: 10.1016/j.neuron.2024.04.017

Ten recommendations for reducing the carbon footprint of research computing in human neuroimaging

Autori: Nicholas E. Souter, Loïc Lannelongue, Gabrielle Samuel, Chris Racey, Lincoln J. Colling, Nikhil Bhagwat, Raghavendra Selvan, Charlotte L. Rae
Pubblicato in: Imaging Neuroscience, 2023, ISSN 0270-6474
Editore: MIT Press Direct
DOI: 10.1162/imag_a_00043

Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation

Autori: Boserup, Nicklas; Selvan, Raghavendra
Pubblicato in: Boserup , N & Selvan , R 2023 , Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation . in Proceedings of the Northern Lights Deep Learning Workshop 2023 . Septentrio Academic Publishing , Proceedings of the Northern Lights Deep Learning Workshop , vol. 4 , 2023 Northern Lights Deep Learning Workshop - NLD 2023 , Tromsø , Norway , 10/01/2023 . https://doi.org/10.7557/18.6798, 2023, ISSN 2703-6928
Editore: Proceedings of the Northern Lights Deep Learning Workshop
DOI: 10.48550/arxiv.2208.10779

A Knowledge Distillation Framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image

Autori: Bhatt, Jwalin; Zharov, Yaroslav; Suh, Sungho; Baumbach, Tilo; Heuveline, Vincent; Lukowicz, Paul
Pubblicato in: Crossref, 2023, ISSN 1945-8452
Editore: IEEE
DOI: 10.48550/arxiv.2302.12562

Energy-Efficient, Low-Latency and Non-contact Eye Blink Detection with Capacitive Sensing

Autori: Mengxi Liu, Sizhen Bian, Zimin Zhao, Bo Zhou, Paul Lukowicz
Pubblicato in: Frontiers in Computer Science, 2024, ISSN 1664-3224
Editore: Frontiers
DOI: 10.3389/fcomp.2024.1394397

Operating Critical Machine Learning Models in Resource Constrained Regimes

Autori: Selvan, Raghavendra; Schön, Julian; Dam, Erik B
Pubblicato in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops ISBN: 9783031474248, 2023, ISSN 1572-8080
Editore: Springer
DOI: 10.48550/arxiv.2303.10181

Novel adaptive quantization methodology for 8-bit floating-point DNN training.

Autori: Hassani Sadi, M., Sudarshan, C. & Wehn N.
Pubblicato in: Springer Journal of Design Automation for Embedded Systems (2023), 2024, ISSN 1572-8080
Editore: Springer
DOI: 10.1007/s10617-024-09282-2

Conference proceedings (8)

Energy Efficiency Impact of Processing in Memory: A Comprehensive Review of Workloads on the UPMEM Architecture

Autori: Yann Falevoz & Julien Legriel
Pubblicato in: Euro-Par 2023: Parallel Processing Workshops, 2024, ISSN 0302-9743
Editore: Springer Cham
DOI: 10.1007/978-3-031-48803-0_13

EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search

Autori: Pedram Bakhtiarifard; Christian Igel; Raghavendra Selvan
Pubblicato in: 2024, ISSN 2379-190X
Editore: IEEE
DOI: 10.1109/ICASSP48485.2024.10448303

Activation Compression of Graph Neural Networks Using Block-Wise Quantization with Improved Variance Minimization

Autori: Eliassen, Sebastian; Selvan, Raghavendra
Pubblicato in: Crossref, 2024, ISSN 2379-190X
Editore: IEEE
DOI: 10.48550/arxiv.2309.11856

Probabilistic feature matching for fast scalable visual prompting

Autori: Thomas Frick∗ , Cezary Skura∗ , Filip M. Janicki∗ , Roy Assaf , Niccolo Avogaro , Daniel Caraballo , Yagmur G. Cinar , Brown Ebouky , Ioana Giurgiu , Takayuki Katsuki , Piotr Kluska , Cristiano Malossi , Haoxiang Qiu , Tomoya Sakai , Florian Scheidegger
Pubblicato in: International Joint Conference for Artificial Intelligence (IJCAI 2024), August 2024, 2024, ISSN 0000-0000
Editore: IJCAI

Latent Inspector: An Interactive Tool for Probing Neural Network Behaviors Through Arbitrary Latent Activation.

Autori: Daniel Geißler, Bo Zhou, Paul Lukowicz.
Pubblicato in: International Joint Conference for Artificial Intelligence (IJCAI 2023), May 2023, 2023
Editore: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence

CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition

Autori: Mengxi Liu, Zimin Zhao, Daniel Geißler, Bo Zhou, Sungho Suh, Paul Lukowicz
Pubblicato in: AAAI 2024 Sustainable AI workshop, January 2024, 2024, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/arXiv.2401.05426

The Power of Training: How Different Neural Network Setups Influence the Energy Demand

Autori: Daniel Geißler, Bo Zhou, Mengxi Liu, Sungho Suh, Paul Lukowicz
Pubblicato in: AAAI 2024 Sustainable AI workshop, January 2024, 2024, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/arXiv.2401.01851Focustolearnmore

FieldHAR: A Fully Integrated End-to-End RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors

Autori: Mengxi Liu; Bo Zhou; Zimin Zhao; Hyeonseok Hong; Hyun Kim; Sungho Suh; Vitor Fortes Rey; Paul Lukowicz.
Pubblicato in: 2023, ISSN 2160-052X
Editore: IEEE
DOI: 10.1109/ASAP57973.2023.00029