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

Información del proyecto

SustainML

Identificador del acuerdo de subvención: 101070408

DOI

10.3030/101070408

Fecha de la firma de la CE 20 Junio 2022

Fecha de inicio 1 Octubre 2022

Fecha de finalización 30 Junio 2026

Financiado con arreglo a

• Digital, Industry and Space

Coste total

€ 3 742 855,00

Aportación de la UE

€ 3 742 855,00

Coordinado por

PROYECTOS Y SISTEMAS DE MANTENIMIENTO SL
Spain

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

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

Publicaciones

Other (1)

Adaptive Conformal Regression with Jackknife+ Rescaled Scores

Autores: Deutschmann, Nicolas; Rigotti, Mattia; Martinez, Maria Rodriguez
Publicado en: 2023, ISSN 0000-0000
Editor: Transactions on Machine Learning Research, TMLR 2024
DOI: 10.48550/arxiv.2305.19901

Peer reviewed articles (7)

Mixed selectivity: Cellular computations for complexity

Autores: KM Tye, EK Miller, FH Taschbach, MK Benna, M Rigotti, S Fusi
Publicado en: NEURON, 2024, ISSN 1097-4199
Editor: NEURON
DOI: 10.1016/j.neuron.2024.04.017

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

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

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

Autores: Boserup, Nicklas; Selvan, Raghavendra
Publicado en: 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
Editor: 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

Autores: Bhatt, Jwalin; Zharov, Yaroslav; Suh, Sungho; Baumbach, Tilo; Heuveline, Vincent; Lukowicz, Paul
Publicado en: Crossref, 2023, ISSN 1945-8452
Editor: IEEE
DOI: 10.48550/arxiv.2302.12562

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

Autores: Mengxi Liu, Sizhen Bian, Zimin Zhao, Bo Zhou, Paul Lukowicz
Publicado en: Frontiers in Computer Science, 2024, ISSN 1664-3224
Editor: Frontiers
DOI: 10.3389/fcomp.2024.1394397

Operating Critical Machine Learning Models in Resource Constrained Regimes

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

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

Autores: Hassani Sadi, M., Sudarshan, C. & Wehn N.
Publicado en: Springer Journal of Design Automation for Embedded Systems (2023), 2024, ISSN 1572-8080
Editor: 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

Autores: Yann Falevoz & Julien Legriel
Publicado en: Euro-Par 2023: Parallel Processing Workshops, 2024, ISSN 0302-9743
Editor: Springer Cham
DOI: 10.1007/978-3-031-48803-0_13

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

Autores: Pedram Bakhtiarifard; Christian Igel; Raghavendra Selvan
Publicado en: 2024, ISSN 2379-190X
Editor: IEEE
DOI: 10.1109/ICASSP48485.2024.10448303

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

Autores: Eliassen, Sebastian; Selvan, Raghavendra
Publicado en: Crossref, 2024, ISSN 2379-190X
Editor: IEEE
DOI: 10.48550/arxiv.2309.11856

Probabilistic feature matching for fast scalable visual prompting

Autores: 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
Publicado en: International Joint Conference for Artificial Intelligence (IJCAI 2024), August 2024, 2024, ISSN 0000-0000
Editor: IJCAI

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

Autores: Daniel Geißler, Bo Zhou, Paul Lukowicz.
Publicado en: International Joint Conference for Artificial Intelligence (IJCAI 2023), May 2023, 2023
Editor: 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

Autores: Mengxi Liu, Zimin Zhao, Daniel Geißler, Bo Zhou, Sungho Suh, Paul Lukowicz
Publicado en: AAAI 2024 Sustainable AI workshop, January 2024, 2024, ISSN 2331-8422
Editor: arXiv
DOI: 10.48550/arXiv.2401.05426

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

Autores: Daniel Geißler, Bo Zhou, Mengxi Liu, Sungho Suh, Paul Lukowicz
Publicado en: AAAI 2024 Sustainable AI workshop, January 2024, 2024, ISSN 2331-8422
Editor: 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

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