001050051 001__ 1050051
001050051 005__ 20251219160619.0
001050051 0247_ $$2arXiv$$aarXiv:2511.05479
001050051 037__ $$aFZJ-2025-05765
001050051 088__ $$2arXiv$$aarXiv:2511.05479
001050051 1001_ $$0P:(DE-Juel1)194719$$aAksoy, Alperen$$b0$$ufzj
001050051 245__ $$aFPGA-Based Real-Time Waveform Classification
001050051 260__ $$c2025
001050051 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1766156563_16229
001050051 3367_ $$2ORCID$$aWORKING_PAPER
001050051 3367_ $$028$$2EndNote$$aElectronic Article
001050051 3367_ $$2DRIVER$$apreprint
001050051 3367_ $$2BibTeX$$aARTICLE
001050051 3367_ $$2DataCite$$aOutput Types/Working Paper
001050051 500__ $$aTWEPP25 proceedings paper pre-print
001050051 520__ $$aFor self-triggered readout of SiPM sum signals, a waveform classification can aid a simple threshold trigger to reliably extract calorimetric particle hit information online at an early stage and thus reduce the volume of transmitted data. Typically, the ADC data acquisition is based on FPGAs for edge data processing. In this study, we consider look-up-table-based neural-networks and address challenges of binary multi-layer neural networks' layout, footprint, performance and training. We show that these structures can be trained using a genetic algorithm and achieve the inference latency compatible with dead-time free processing online.
001050051 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001050051 588__ $$aDataset connected to arXivarXiv
001050051 7001_ $$0P:(DE-Juel1)171927$$aBekman, Ilja$$b1$$eCorresponding author$$ufzj
001050051 7001_ $$0P:(DE-Juel1)180232$$aEguzo, Chimezie$$b2$$ufzj
001050051 7001_ $$0P:(DE-Juel1)159350$$aGrewing, Christian$$b3$$ufzj
001050051 7001_ $$0P:(DE-Juel1)145837$$aZambanini, Andre$$b4$$ufzj
001050051 8564_ $$uhttps://arxiv.org/abs/2511.05479
001050051 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)194719$$aForschungszentrum Jülich$$b0$$kFZJ
001050051 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171927$$aForschungszentrum Jülich$$b1$$kFZJ
001050051 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180232$$aForschungszentrum Jülich$$b2$$kFZJ
001050051 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)159350$$aForschungszentrum Jülich$$b3$$kFZJ
001050051 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)145837$$aForschungszentrum Jülich$$b4$$kFZJ
001050051 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001050051 920__ $$lyes
001050051 9201_ $$0I:(DE-Juel1)PGI-4-20110106$$kPGI-4$$lIntegrated Computing Architectures$$x0
001050051 980__ $$apreprint
001050051 980__ $$aEDITORS
001050051 980__ $$aVDBINPRINT
001050051 980__ $$aI:(DE-Juel1)PGI-4-20110106
001050051 980__ $$aUNRESTRICTED