001055111 001__ 1055111
001055111 005__ 20260227202313.0
001055111 0247_ $$2doi$$a10.5281/ZENODO.18770020
001055111 0247_ $$2datacite_doi$$a10.34734/FZJ-2026-01868
001055111 037__ $$aFZJ-2026-01868
001055111 041__ $$aEnglish
001055111 1001_ $$0P:(DE-Juel1)194719$$aAksoy, Alperen$$b0$$eCorresponding author$$ufzj
001055111 1112_ $$adeRSE26 - 6th conference for Research Software Engineering & 1st Stuttgart Research Software Day$$cStuttgart$$d2026-03-03 - 2026-03-05$$gdeRSE26 & SRSD1$$wGermany
001055111 245__ $$aEmbedded Artificial Neural Networks for Energy-Restricted Edge-Computing Applications
001055111 260__ $$c2026
001055111 3367_ $$033$$2EndNote$$aConference Paper
001055111 3367_ $$2BibTeX$$aINPROCEEDINGS
001055111 3367_ $$2DRIVER$$aconferenceObject
001055111 3367_ $$2ORCID$$aCONFERENCE_POSTER
001055111 3367_ $$2DataCite$$aOutput Types/Conference Poster
001055111 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1772112443_17387$$xAfter Call
001055111 520__ $$aThe development of energy-efficient and fast machine learning methods plays an increasingly important role in experimental physics, where data analysis and control tasks often need to operate under strict resource constraints. In these contexts, machine learning models can automate complex calibration and analysis tasks while enabling on-device data processing close to the experimental sensors.One representative application presented on this poster concerns the automated calibration of semiconductor spin qubits, while the outlook highlights extensions toward edge-computing approaches in detector systems.The automated calibration of quantum dots is a key prerequisite for realizing scalable quantum computers. In particular, the analysis of charge stability diagrams, used to detect charge transitions in quantum dots, represents a complex and time-consuming task. Neural networks, especially U-Net architectures, offer the potential to automate this process by reliably recognizing relevant patterns in simulated and experimental measurement data. State-of-the-art networks have already been successfully trained for this purpose.However, there remains significant potential for optimization to enable space- and energy-efficient integration close to the quantum bits within the cryostat.We have investigated the use of quantized neural networks for energy-efficient quantum dot calibration. The goal is to analyze the impact of post-training quantization and quantization-aware training on detection quality, as well as the general effects of quantization on memory requirements and inference speed. Three U-Nets with different architectures, parameter counts, and input dimensions serve as model bases, applied to simulated charge stability diagrams. The results show that appropriate quantization strategies can reduce memory usage without significantly affecting detection quality.The findings of this work contribute to the integration of energy-efficient machine learning methods into experimental quantum computing environments, thereby supporting overall scalability.Building on these results, the approach is extended toward the use of binarized neural networks (BNNs) to push energy efficiency and faster inference even further. Within edge computing applications, current efforts focus on implementing and demonstrating such networks on FPGA hardware, aiming to exploit binary-weight computation and hardware-level parallelism for minimal latency and power consumption. Beyond quantum dot calibration, these methods are also being investigated for other scientific applications, such as the autonomous self-triggering radio detection of extensive air showers, highlighting the broader potential of hardware-embedded AI for resource-constrained experimental environments.
001055111 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001055111 588__ $$aDataset connected to DataCite
001055111 650_7 $$2Other$$aQuantum Dot Calibration
001055111 650_7 $$2Other$$aEnergy-Efficient Machine Learning
001055111 650_7 $$2Other$$aQuantized Neural Networks
001055111 650_7 $$2Other$$aU-Net
001055111 650_7 $$2Other$$aEdge Computing
001055111 650_7 $$2Other$$aFPGA
001055111 650_7 $$2Other$$aBinary Neural Networks
001055111 650_7 $$2Other$$aModel Compression
001055111 650_7 $$2Other$$aReal-Time Inference
001055111 7001_ $$0P:(DE-Juel1)173094$$aFleitmann, Sarah$$b1$$ufzj
001055111 7001_ $$0P:(DE-Juel1)171927$$aBekman, Ilja$$b2$$ufzj
001055111 7001_ $$0P:(DE-HGF)0$$aDorosti, Qader$$b3
001055111 7001_ $$0P:(DE-Juel1)133952$$aVogelbruch, Jan-Friedrich$$b4$$ufzj
001055111 7001_ $$0P:(DE-HGF)0$$aDimitrov, Vesselin$$b5
001055111 7001_ $$0P:(DE-Juel1)170099$$aHader, Fabian$$b6$$ufzj
001055111 7001_ $$0P:(DE-Juel1)142562$$avan Waasen, Stefan$$b7$$ufzj
001055111 773__ $$a10.5281/ZENODO.18770020
001055111 8564_ $$uhttps://juser.fz-juelich.de/record/1055111/files/deRSE26-Poster.pdf$$yOpenAccess
001055111 909CO $$ooai:juser.fz-juelich.de:1055111$$popenaire$$popen_access$$pVDB$$pdriver
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)194719$$aForschungszentrum Jülich$$b0$$kFZJ
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173094$$aForschungszentrum Jülich$$b1$$kFZJ
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171927$$aForschungszentrum Jülich$$b2$$kFZJ
001055111 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a University of Siegen$$b3
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)133952$$aForschungszentrum Jülich$$b4$$kFZJ
001055111 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a University of Siegen$$b5
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)170099$$aForschungszentrum Jülich$$b6$$kFZJ
001055111 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)142562$$aForschungszentrum Jülich$$b7$$kFZJ
001055111 9131_ $$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
001055111 9141_ $$y2026
001055111 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001055111 9201_ $$0I:(DE-Juel1)PGI-4-20110106$$kPGI-4$$lIntegrated Computing Architectures$$x0
001055111 980__ $$aposter
001055111 980__ $$aVDB
001055111 980__ $$aUNRESTRICTED
001055111 980__ $$aI:(DE-Juel1)PGI-4-20110106
001055111 9801_ $$aFullTexts