Platform for Open Development of Systems of Artificial Intelligence

Rezultaty

Conceived as a dissemination tool to interest stakeholders and the public in the project. Project partners will distribute it at various events.

Bonseyes video

Conceived as a dissemination tool to interest researchers, stakeholders and the public in the project, also addressing an audience which can not easily be reached via other means. The video will be made available on the Bonseyes website and channels such as youtube.

Website

Public project website serving as a dissemination gateway.

Revised AI Marketplace

Revised Marketplace development based on the results from Open Developer Community Validation.

Validation Report

Documentation of the Bonseyes use case validation results and of the open developer community validation results.

Data Marketplace Report

Documentation of the data marketplace design and implementation.

Demonstrator Proof of Concepts

Report detailing demonstrator achievements.

Initial Platform Deployment Methods and Tools
Initial Deep Learning Methods
Revised Deep Learning Methods
Revised Platform Deployment Methods and Tools

Publikacje

Privacy and Trust in Cloud-Based Marketplaces for AI and Data Resources

Autorzy: Ahmadi , Vida; Tutschku , Kurt
Opublikowane w: IFIP Advances in Information and Communication Technology, Numer 5, 2017, Strona(/y) 223-225, ISBN 3319-591703
Wydawca: Springer

Performance Analysis and Optimization of Sparse Matrix-Vector Multiplication on Modern Multi- and Many-Core Processors

Autorzy: Athena Elafrou, Georgios Goumas, Nectarios Koziris
Opublikowane w: 2017 46th International Conference on Parallel Processing (ICPP), 2017, Strona(/y) 292-301, ISBN 978-1-5386-1042-8
Wydawca: IEEE
DOI: 10.1109/ICPP.2017.38

Optimal DNN primitive selection with partitioned boolean quadratic programming

Autorzy: Andrew Anderson, David Gregg
Opublikowane w: Proceedings of the 2018 International Symposium on Code Generation and Optimization - CGO 2018, 2018, Strona(/y) 340-351, ISBN 9781-450356176
Wydawca: ACM Press
DOI: 10.1145/3179541.3168805

Pricing of Data Products in Data Marketplaces

Autorzy: Samuel A. Fricker, Yuliyan V. Maksimov
Opublikowane w: Lecture Notes in Business Information Processing (LNBIP), Numer 304, 2017, Strona(/y) 49-66, ISBN 978-3-319-69190-9
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-319-69191-6_4

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks

Autorzy: Jack Turner, Jose Cano, Valentin Radu, Elliot J. Crowley, Michael O'Boyle, Amos Storkey
Opublikowane w: 2018 IEEE International Symposium on Workload Characterization (IISWC), 2018, Strona(/y) 101-110, ISBN 978-1-5386-6780-4
Wydawca: IEEE
DOI: 10.1109/IISWC.2018.8573503

QUENN - QUantization engine for low-power neural networks

Autorzy: Miguel de Prado, Maurizio Denna, Luca Benini, Nuria Pazos
Opublikowane w: Proceedings of the 15th ACM International Conference on Computing Frontiers - CF '18, 2018, Strona(/y) 36-44, ISBN 9781-450357616
Wydawca: ACM Press
DOI: 10.1145/3203217.3203282

Towards Privacy Requirements for Collaborative Development of AI Applications

Autorzy: Ahmadi Mehri, Vida; Ilie, Dragos; Tutschku, Kurt
Opublikowane w: Numer 1, 2018
Wydawca: BTH

Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems

Autorzy: de Prado, Miguel; Pazos, Nuria; Benini, Luca
Opublikowane w: Numer 1, 2018
Wydawca: ArXiv

Distilling with Performance Enhanced Students

Autorzy: Turner, Jack; Crowley, Elliot J.; Radu, Valentin; Cano, José; Storkey, Amos; O'Boyle, Michael
Opublikowane w: Numer 1, 2018
Wydawca: Proceedings of 27th International Conference on Artificial Neural Networks

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length

Autorzy: Jastrzębski, Stanislaw; Kenton, Zachary; Ballas, Nicolas; Fischer, Asja; Bengio, Yoshua; Storkey, Amos
Opublikowane w: Jastrzębski , S , Kenton , Z , Ballas , N , Fischer , A , Bengio , Y & Storkey , A 2019 , ' On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length ' , Paper presented at Seventh International Conference on Learning Representations , New Orleans , United States , 6/05/19 - 9/05/19 ., Numer 1, 2018
Wydawca: Seventh International Conference on Learning Representations (2019)

DNN's Sharpest Directions Along the SGD Trajectory

Autorzy: Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey
Opublikowane w: 2018
Wydawca: ArXiv

Three Factors Influencing Minima in SGD

Autorzy: Stanisław Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey
Opublikowane w: 2018
Wydawca: ArXiv

Privacy and DRM Requirements for Collaborative Development of AI Applications

Autorzy: Vida Ahmadi Mehri, Dragos Ilie, Kurt Tutschku
Opublikowane w: Proceedings of the 13th International Conference on Availability, Reliability and Security - ARES 2018, 2018, Strona(/y) 1-8, ISBN 9781-450364485
Wydawca: ACM Press
DOI: 10.1145/3230833.3233268

Designing a Secure IoT System Architecture from a Virtual Premise for a Collaborative AI Lab

Autorzy: Mehri, V. A., Ilie, D. & Tutschku, K.
Opublikowane w: 2019
Wydawca: Workshop on Decentralized IoT Systems and Security (DISS) 2019

Framework for Analysis of Multi-party Collaboration

Autorzy: Yuliyan V. Maksimov, Samuel A. Fricker
Opublikowane w: 2019 IEEE 27th International Requirements Engineering Conference Workshops (REW), 2019, Strona(/y) 44-53, ISBN 978-1-7281-5165-6
Wydawca: IEEE
DOI: 10.1109/rew.2019.00013

Distributed Ledger for Provenance Tracking of Artificial Intelligence Assets

Autorzy: Philipp Lüthi, Thibault Gagnaux, Marcel Gygli
Opublikowane w: 2019
Wydawca: ArXiv

Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks

Autorzy: Andrew Anderson, Michael Doyle, David Gregg
Opublikowane w: 2019 IEEE 26th Symposium on Computer Arithmetic (ARITH), 2019, Strona(/y) 61-68, ISBN 978-1-7281-3366-9
Wydawca: IEEE
DOI: 10.1109/arith.2019.00018

Performance-Oriented Neural Architecture Search

Autorzy: Andrew Anderson, Jing Su, Rozenn Dahyot, David Gregg
Opublikowane w: 2020
Wydawca: ArXiv

BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget

Autorzy: Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos Storkey, Gavin Gray
Opublikowane w: 2020
Wydawca: ArXiv

Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs

Autorzy: Valentin Radu, Kuba Kaszyk, Yuan Wen, Jack Turner, Jose Cano, Elliot J. Crowley, Bjorn Franke, Amos Storkey, Michael O'Boyle
Opublikowane w: 2019
Wydawca: ArXiv

IoT meets distributed AI - Deployment scenarios of Bonseyes AI applications on FIWARE

Autorzy: Lucien Moor, Lukas Bitter, Miguel De Prado, Nuria Pazos, Nabil Ouerhani
Opublikowane w: 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC), 2019, Strona(/y) 1-2, ISBN 978-1-7281-1025-7
Wydawca: Piscataway, New Jersey, USA
DOI: 10.1109/ipccc47392.2019.8958742

How to train your MAML

Autorzy: Antoniou, Antreas; Edwards, Harrison; Storkey, Amos
Opublikowane w: Seventh International Conference on Learning Representations, 2019
Wydawca: ICLR 2019

BONSEYES - Platform for Open Development of Systems of Artificial Intelligence: Invited paper

Autorzy: Tim Llewellynn, Sebastian Koller, Georgios Goumas, Peter Leitner, Ganesh Dasika, Lei Wang, Kurt Tutschku, M. Milagro Fern?ndez-Carrobles, Oscar Deniz, Samuel Fricker, Amos Storkey, Nuria Pazos, Gordana Velikic, Kirsten Leufgen, Rozenn Dahyot
Opublikowane w: Proceedings of the Computing Frontiers Conference on ZZZ - CF'17, 2017, Strona(/y) 299-304, ISBN 9781-450344876
Wydawca: ACM Press
DOI: 10.1145/3075564.3076259

Parallel Multi Channel convolution using General Matrix Multiplication

Autorzy: Aravind Vasudevan, Andrew Anderson, David Gregg
Opublikowane w: 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP), 2017, Strona(/y) 19-24, ISBN 978-1-5090-4825-0
Wydawca: IEEE
DOI: 10.1109/ASAP.2017.7995254

Flexible Privacy and High Trust in the Next Generation Internet - The Use Case of a Cloud-based Marketplace for AI

Autorzy: Mehri, Vida. A., Tutschku, Kurt
Opublikowane w: SNCNW - Swedish National Computer Networking Workshop, Halmstad, 2017
Wydawca: Halmstad university

Low-memory GEMM-based convolution algorithms for deep neural networks

Autorzy: Anderson, Andrew; Vasudevan, Aravind; Keane, Cormac; Gregg, David
Opublikowane w: Numer 2, 2017
Wydawca: ArXiv

Moonshine: Distilling with Cheap Convolutions

Autorzy: Crowley, Elliot J.; Gray, Gavin; Storkey, Amos
Opublikowane w: Numer 1, 2017
Wydawca: arXiv

Accelerating Deep Neural Networks on Low Power Heterogeneous Architectures.

Autorzy: Loukadakis, M., Cano, J. & O’Boyle, M.
Opublikowane w: 11th International Workshop on Programmability and Architectures for Heterogeneous Multicores (MULTIPROG-2018). 11th International Workshop on Programmability and Architectures for Heterogeneous Multicores (MULTIPROG-2018), Manchester, United Kingdom, 24 January, 2018
Wydawca: -

Separable Layers Enable Structured Efficient Linear Substitutions

Autorzy: Gray, Gavin; Crowley, Elliot J.; Storkey, Amos
Opublikowane w: Numer 1, 2019
Wydawca: ArXiv

AI Pipeline - bringing AI to you. End-to-end integration of data, algorithms and deployment tools

Autorzy: de Prado, Miguel; Su, Jing; Dahyot, Rozenn; Saeed, Rabia; Keller, Lorenzo; Vallez, Noelia
Opublikowane w: Numer 1, 2019
Wydawca: ArXiv

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

Autorzy: Antoniou, Antreas; Storkey, Amos
Opublikowane w: Numer 1, 2019
Wydawca: ArXiv

A Closer Look at Structured Pruning for Neural Network Compression

Autorzy: Crowley, Elliot J.; Turner, Jack; Storkey, Amos; O'Boyle, Michael
Opublikowane w: Numer 1, 2019
Wydawca: ArXiv

RecNets: Channel-wise Recurrent Convolutional Neural Networks

Autorzy: Retsinas, G., Elafrou, A., Goumas, G. & Maragos, P.
Opublikowane w: 2020
Wydawca: arXiv.org

Artifact Compatibility for Enabling Collaboration in the Artificial Intelligence Ecosystem

Autorzy: Yuliyan V. Maksimov, Samuel A. Fricker, Kurt Tutschku
Opublikowane w: Software Business - 9th International Conference, ICSOB 2018, Tallinn, Estonia, June 11–12, 2018, Proceedings, Numer 336, 2018, Strona(/y) 56-71, ISBN 978-3-030-04839-6
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-030-04840-2_5

Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio

Autorzy: Stanislaw Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey
Opublikowane w: Artificial Neural Networks and Machine Learning – ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III, Numer 11141, 2018, Strona(/y) 392-402, ISBN 978-3-030-01423-0
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-030-01424-7_39

Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks

Autorzy: Antreas Antoniou, Amos Storkey, Harrison Edwards
Opublikowane w: Artificial Neural Networks and Machine Learning – ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III, Numer 11141, 2018, Strona(/y) 594-603, ISBN 978-3-030-01423-0
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-030-01424-7_58

Towards Secure Collaborative AI Service Chains

Autorzy: Vida Ahmadi Mehri
Opublikowane w: 2019
Wydawca: Blekinge Institute of Technology

Robustness to adversarial examples can be improved with overfitting

Autorzy: Oscar Deniz, Anibal Pedraza, Noelia Vallez, Jesus Salido, Gloria Bueno
Opublikowane w: International Journal of Machine Learning and Cybernetics, Numer 11/4, 2020, Strona(/y) 935-944, ISSN 1868-8071
Wydawca: Springer Science + Business Media
DOI: 10.1007/s13042-020-01097-4

Wyszukiwanie danych OpenAIRE...

Rezultaty

Publikacje

Udostępnij tę stronę

Pobierz