Brian Clerkin

dblp:139/9431 · DBLP profile ↗
← Back
4ranked-venue papers
1as first author
3since 2021 · last 2026
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 3 · 3 since 2021Software engineering, systems software and programming languages · 1 · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author
YearPublicationVenuePosition
2026 Multi-Partner Project: dAIEDGE - A Network of Excellence for Distributed, Trustworthy, Efficient and Scalable AI at the Edge
abstract
The dAIEDGE Network of Excellence (NoE) seeks to strengthen and support the development of a dynamic European cutting-edge Artificial intelligence (AI) ecosystem under the umbrella of the European Lighthouse for AI, and to sustain the development of advanced AI. dAIEDGE fosters the exchange of ideas, concepts, and trends on cutting-edge next generation AI, creating links between ecosystem actors to help both the European Commission (EC) and the European Union (EU) and the peripheral AI constituency identify strategies for future developments in Europe. Our main objective is to advance Europe’s innovation and technology base by developing a comprehensive policy and governance approach to AI in order for the EU to become a world leader in innovation in the data economy and its applications.
Alain Pagani, Haralampos-G. D. Stratigopoulos, Aysajan Abidin, Mhd Rashed Al Koutayni, Luca Benini, Angelos Bilas, Alessandro Capotondi, Roberto Cavicchioli, Brian Clerkin, Oscar Déniz-Suárez, Margaux Divernois, Baptiste Dupertuis, Dorvan Favre, Giulio Gambardella, Ander García Gangoiti, Carlo Augusto Grazia, Dominik Günzel, Jude Haris, Klodjan K. Hidri, Maïck Huguenin-Vuillemin, Manal Jammal, Paul Kling, Christos Kozanitis, Xavier Lessage, Srikanth Mandapati, Philippe Massonet, Alfio Di Mauro, Varesh Mishra, Juan Odriozola, Javier Parra 0001, Nuria Pazos, Viviane Potocnik, Miguel de Prado, Rohit Prasad, Spyridon Raptis, Gregoire Rebstein, Ignacio Sanudo Olmedo, Mohamed Selim, Chinmay Satish Shrivastav, Noelia Vállez, Giorgos Vasiliadis, Micaela Verrucchi, Enrico Vincenzi, Damian Vizár, Devendra Vyas, Stefan Wiehle
DATE10
2026 Towards Resilient Transformer-Encoders: Fault Injection and Hardware Agnostic Error Mitigation
Vishal Thomas, Ussama Zahid, Giulio Gambardella, Sumeet Sapkal, Haralampos-G. D. Stratigopoulos, Brian Clerkin
ETS6
2025 On the Fault Sensitivity of Natural Language Embeddings Computation
Sumeet Sapkal, Ussama Zahid, Giulio Gambardella, Haralampos-G. D. Stratigopoulos, Brian Clerkin
ETS5
2001 Optimum design of overlapping discrete multitone filter banks for digital subscriber line channels
abstract
A new approach to the design of optimum transmultiplexer filter banks for overlapping discrete multitone (ODMT) multicarrier modulation is presented. ODMT has been proposed for use in high-speed data communications over twisted pair copper wires such as digital subscriber lines (DSL), due to its ability to cope well with channel degradations and noise. We propose a new design technique which minimizes the overall interference. We consider the effect of the time domain overlap between successive symbol waveforms by considering each modulation filter as a series of filter components in time. We explicitly incorporate some knowledge of the digital subscriber line channel into our design technique, to account for the effects of time dispersion and frequency distortion. Numerical simulations show that the optimisation of the components in the mixed time-frequency domain leads to an increase in the signal-to-interference ratio of the order of 0.2-0.3 dB.
Brian Clerkin, Conor Heneghan
ICASSP1