publ-eml.bib

@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -q -ob publ-eml.bib --remove keywords -c 'key : "\beml\b"' /home/jantsch/Website/jantsch.se/AxelJantsch/publist.bib}}
@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -q -oc /home/jantsch/Website/jantsch.se/AxelJantsch/citefile -c '(( author : "Jantsch" or ( editor : "Jantsch" and $type : "book" ))
	    and ( not ( $key : "presentation" ))
	    and ( not ( $type : "techreport" ))
	    and ( not ( $type : "misc" ))
	    and ( not ( annotate : "not reviewed" ))
	    and ( not ( note : "Under submission" )))
	    or $key = "hauer:2021a"
	    '}}
@inproceedings{janser:2026a,
  author = {Jonas Janser and Matthias Wess and Dominik Dallinger
                  and Matthias Bittner and Daniel Schn\"{o}ll and Axel Jantsch},
  title = {Spring reverb emulation with hybrid gated
                  convolutional networks and state space models},
  key = {eml,cdl},
  booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing},
  year = 2026,
  month = {May},
  address = {Barcelona, Spain},
  url = {http://jantsch.se/AxelJantsch/papers/2026/JonasJanser-ICASSP2026.pdf}
}
@article{berg:2026a,
  author = {Berg, Oscar Artur Bernd and Saqib, Eiraj and
                  Jantsch, Axel and Leal, Isaac S\'{a}nchez and Shallari,
                  Irida and Krug, Silvia and O'Nils, Mattias},
  journal = {IEEE Access},
  title = {{BranchySplit}: Dynamic Partitioning and Early Exits
                  for Accelerated Edge Inference},
  year = 2026,
  pages = {1-1},
  key = {eml},
  doi = {10.1109/ACCESS.2026.3651845}
}
@article{leal:2025a,
  author = {Leal, Isaac S\'{a}nchez and Berg, Oscar Artur Bernd
                  and Krug, Silvia and Saqib, Eiraj and Shallari,
                  Irida and Jantsch, Axel and O'Nils, Mattias and
                  Nordstr\"{o}m, Tomas},
  journal = {IEEE Access},
  title = {Quantization Compensator Network: Server-Side
                  Feature Reconstruction in Partitioned IoT Systems},
  year = 2025,
  volume = 13,
  pager = {186488-186508},
  pages = {1-1},
  key = {eml},
  url = {http://jantsch.se/AxelJantsch/papers/2025/IsaacSLeal-QCN-IEEEAccess.pdf},
  doi = {10.1109/ACCESS.2025.3627072}
}
@inproceedings{schnoell:2024a,
  author = { Daniel Schn\"{o}ll and Dominik Dallinger and
                  Matthias Wess and Matthias Bittner and Axel Jantsch
                  },
  title = { Towards Optimal Implementations of Neural Networks
                  on Micro-Controller},
  key = {cdl,eml},
  booktitle = {Proceedings of the ITEM Workshop - IoT, Edge, and
                  Mobile for Embedded Machine Learning},
  year = 2024,
  month = {September},
  address = {Vilnius, Lithuania},
  url = {http://jantsch.se/AxelJantsch/papers/2024/DanielSchnoell-ITEM.pdf}
}
@inproceedings{schnoell:2025a,
  author = { Daniel Schn\"{o}ll and Matthias Bittner and Axel
                  Jantsch },
  title = {Implementation and Optimization of Diagonal State Space Models},
  booktitle = {Proceedings of the ITEM Workshop - IoT, Edge, and
                  Mobile for Embedded Machine Learning},
  year = 2025,
  month = {September},
  address = {Porto, Portugal},
  key = {eml,cdl},
  url = {http://jantsch.se/AxelJantsch/papers/2025/DanielSchnoell-ITEM.pdf}
}
@inproceedings{rusy:2025a,
  author = {Karel Rus\'{y} and Fabian Seiler and David Breuss
                  and Axel Jantsch},
  title = { {SYNAD}: A Synthetic Object Injection Methodology
                  for Enhanced Anomaly Detection },
  key = {eml,cdl},
  booktitle = { Proceedings of the 2025 8th International
                  Conference on Machine Vision and Applications
                  (ICMVA) },
  year = 2025,
  month = {June},
  address = {Melbourne, Australia},
  publisher = {SPIE - The Society of Photo-Optical Instrumentation
                  Engineers },
  doi = {10.1117/12.3078677},
  url = {http://jantsch.se/AxelJantsch/papers/2025/KarelRusy-ICMVA.pdf}
}
@article{berg:2025c,
  author = {Berg, Oscar Artur Bernd and Saqib, Eiraj and
                  Jantsch, Axel and Shallari, Irida and Krug, Silvia
                  and Leal, Isaac S\'{a}nchez and O'Nils, Mattias},
  journal = {IEEE Access},
  title = {{TCL}: Time-dependent Clustering Loss for Optimizing
                  Post-Training Feature Map Quantization for
                  Partitioned DNNs},
  year = 2025,
  key = {eml,cdl},
  pages = {1-1},
  url = {http://jantsch.se/AxelJantsch/papers/2025/OscarBerg-TCL-IEEEAccess.pdf
                  },
  doi = {10.1109/ACCESS.2025.3579107}
}
@inproceedings{dallinger:2025a,
  author = {Dominik Dallinger and Matthias Bittner and Daniel
                  Schn{\"o}ll and Matthias Wess and Axel Jantsch},
  title = { Piano-{SSM}: Diagonal state space models for
                  efficient midi-to-raw audio synthesis},
  key = {eml,cdl},
  booktitle = {Proceedings of the 28th International Conference on
                  Digital Audio Effects (DAFx25)},
  year = 2025,
  month = {September},
  address = {Ancona, Italy},
  url = {
                  http://jantsch.se/AxelJantsch/papers/2025/DominikDallinger-DAFx25.pdf}
}
@inproceedings{berg:2025b,
  author = {Oscar Artur Bernd Berg and Eiraj Saqib and Axel
                  Jantsch and Mattias O'Nils and Irida Shallari and Isaac
                  S\'{a}nchez Leal and Silvia Krug },
  title = { Quantization-Aware Training for Autoencoder-Based
                  Partitioning of {CNNs} },
  key = {eml,cdl},
  booktitle = {Proceedings of the 4th IEEE Workshop on Pervasive
                  and Resource-Constrained Artificial Intelligence
                  (PeRConAI), co-located with IEEE Percom },
  year = 2025,
  month = {March},
  address = {Washington DC, USA},
  note = { Best Paper Award}
}
@inproceedings{berg:2025a,
  author = { Oscar Artur Bernd Berg and  Eiraj Saqib and  Axel
                  Jantsch and  Mattias O'Nils and  Silvia Krug and
                  Irida Shallari and Isaac S\'{a}nchez Leal},
  title = {Efficient Inference of parallel partitioned hybrid-Vision Transformers},
  key = {cdl,eml},
  booktitle = {Proceedings of the 4th Real-time And intelliGent
                  Edge computing workshop (RAGE) at CPS-IOT WEEK },
  year = 2025,
  month = {May},
  address = {Irvine, USA}
}
@inproceedings{shakibhamedan:2024b,
  title = {An Analytical Approach to Enhancing {DNN} Efficiency
                  and Accuracy Using Approximate Multiplication},
  author = {Salar Shakibhamedan and Anice Jahanjoo and Amin
                  Aminifar and Nima Amirafshar and Nima TaheriNejad
                  and Axel Jantsch},
  booktitle = {2nd Workshop on Advancing Neural Network Training:
                  Computational Efficiency, Scalability, and Resource
                  Optimization (WANT@ICML 2024)},
  year = 2024,
  key = {cdl,eml,circuits},
  url = {https://openreview.net/forum?id=rver7enVfY}
}
@incollection{katare:2024a,
  author = {Dewant Katare and Salar Shakibhamedan and Nima
                  Amirafshar and Nima Taherinejad and Axel Jantsch and
                  Marijn Janssen and Aaron Yi Ding },
  title = {Approximation Strategies for Vision Models on Edge
                  Devices: An Accuracy-Efficiency Trade-off },
  booktitle = {TechRxiv},
  key = {eml,circuits},
  month = {December},
  year = 2024,
  doi = {10.36227/techrxiv.173337762.24402407/v1},
  url = {http://jantsch.se/AxelJantsch/papers/2024/DewantKatare-TechRxiv.pdf}
}
@incollection{shakibhamedan:2024a,
  author = {Salar Shakibhamedan and Amin Aminifar and Nima
                  Taherinejad and Axel Jantsch},
  title = { {EASE}: Energy Optimization through Adaptation - A
                  Review of Runtime Energy-Aware Approximate Deep
                  Learning Algorithms},
  booktitle = {TechRxiv},
  key = {eml,survey},
  month = {February},
  year = 2024,
  url = {http://jantsch.se/AxelJantsch/papers/2024/SalarShakibhamedan-TechRxiv.pdf},
  doi = {10.36227/techrxiv.170723230.09169589/v1}
}
@inproceedings{bittner:2024c,
  author = {Bittner, Matthias and Hauer, Daniel and Wess,
                  Matthias and Schnöll, Daniel and Diwold, Konrad and
                  Jantsch, Axel},
  booktitle = {2024 8th International Conference on System
                  Reliability and Safety (ICSRS)},
  title = {Forecasting Load Profiles and Critical Overloads
                  with Uncertainty Quantification for Low Voltage
                  Smart Grids},
  year = 2024,
  pages = {138-147},
  key = {cdl,eml},
  doi = {10.1109/ICSRS63046.2024.10927481}
}
@inproceedings{bittner:2024b,
  author = {Matthias Bittner and Daniel Hauer and Matthias Wess
                  and Dominik Dallinger and Daniel Schn\"{o}ll and
                  Konrad Diwold and Axel Jantsch },
  title = {Interpretable Load Forecasting with Structured State
                  Space Neural Networks },
  key = {cdl,eml},
  booktitle = { Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year = 2024
}
@inproceedings{jantsch:2024b,
  author = {Axel Jantsch and Song Han and Lin Meng and Oliver
                  Bringmann and Haotian Tang and Shang Yang and Hengyi
                  Li and Matthias Wess and Martin Lechner},
  title = {Special Session: Estimation and Optimization of
                  {DNN}s for Embedded Platforms},
  key = {eml,cdl},
  booktitle = {Proceedings of the International Symposium on
                  Hardware Software Codesign},
  year = 2024,
  pages = {21-30},
  month = {October},
  doi = {10.1109/CODES-ISSS60120.2024.00013},
  address = {Raleigh, NC}
}
@inproceedings{leopold:2024a,
  author = {Thomas Leopold and Axel Jantsch},
  title = {Colorado Potato Beetle Dataset and Detection for
                  Monitoring and Management in Potato Fields },
  key = {eml},
  booktitle = {Proceedings of the Austrian Symposion on AI, Robotics and Vision },
  year = 2024,
  address = {Austria},
  url = {http://jantsch.se/AxelJantsch/papers/2024/ThomasLeopold-AIROV.pdf}
}
@inproceedings{bittner:2025c,
  author = {Matthias Bittner and Daniel Schn\"{o}ll and Fabian
                  Seiler and Matthias Wess and Axel Jantsch},
  title = {Modeling Diagonal State Space Models as Electric
                  Circuits for Analog Neural Network Inference},
  key = {eml,cdl,circuit},
  booktitle = {International workshop on Deep Learning meets
                  Neuromorphic Hardware},
  year = 2025,
  month = {September},
  address = {Porto, Portugal},
  note = { Best Poster Award },
  doi = {10.1007/978-3-032-19099-4_30},
  url = {http://jantsch.se/AxelJantsch/papers/2025/MatthiasBittner-AnalogSSM.pdf}
}
@inproceedings{bittner:2025b,
  author = {Matthias Bittner and Daniel Schn\"{o}ll and Dominik
                  Dallinger and Matthias Wess and Axel Jantsch},
  title = {Pruning State Space Models with Model Order
                  Reduction for Efficient Raw Audio Classification},
  key = {cdl,eml},
  booktitle = { European Signal Processing Conference (EUSIPCO) },
  year = 2025,
  month = {September},
  address = {Palermo, Italy},
  doi = {10.23919/EUSIPCO63237.2025.11226287},
  url = {http://jantsch.se/AxelJantsch/papers/2025/MatthiasBittner-Eusipco.pdf}
}
@article{bittner:2025a,
  author = {Bittner, Matthias and Schn{\"o}ll, Daniel and Wess,
                  Matthias and Jantsch, Axel},
  title = {Efficient and interpretable raw audio classification
                  with diagonal state space models},
  journal = {Machine Learning},
  year = 2025,
  month = {Jun},
  day = 19,
  volume = 114,
  number = 8,
  pages = 175,
  key = {cdl,eml},
  abstract = {State Space Models have achieved good performance on
                  long sequence modeling tasks such as raw audio
                  classification. Their definition in continuous time
                  allows for discretization and operation of the
                  network at different sampling rates. However, this
                  property has not yet been utilized to decrease the
                  computational demand on a per-layer basis. We
                  propose a family of hardware-friendly S-Edge models
                  with a layer-wise downsampling approach to adjust
                  the temporal resolution between individual
                  layers. Applying existing methods from linear
                  control theory allows us to analyze state/memory
                  dynamics and provides an understanding of how and
                  where to downsample. Evaluated on the Google Speech
                  Command dataset, our autoregressive/causal S-Edge
                  models range from 8--141k parameters at 90--95{\%}
                  test accuracy in comparison to a causal S5 model
                  with 208k parameters at 95.8{\%} test
                  accuracy. Using our C++17 header-only implementation
                  on an ARM Cortex-M4F the largest model requires
                  103 sec. inference time with 95.19{\%} test
                  accuracy, and the smallest model with 88.01{\%} test
                  accuracy, requires 0.29 sec. Our solutions cover a
                  design space that spans 17x in model size, 358x in
                  inference latency, and 7.18 percentage points in
                  accuracy.},
  issn = {1573-0565},
  doi = {10.1007/s10994-025-06807-z},
  url = {https://doi.org/10.1007/s10994-025-06807-z}
}
@inproceedings{breuss:2024a,
  author = {David Breuss and Karel Rus\'y and Maximilian
                  G\"{o}tzinger and Axel Jantsch},
  title = {Generation of Synthetic Image Anomalies for Analysis
                  and Evaluation },
  key = {cdl,eml},
  booktitle = {Proceedings of the International Conference on
                  Intelligent Systems and Pattern Recognition},
  year = 2024,
  url = {
                  http://jantsch.se/AxelJantsch/papers/2024/DavidBreuss-ISPR.pdf}
}
@inproceedings{bittner:2023b,
  author = {Matthias Bittner and Sanaa Hobeichi and Muhammad
                  Zawish and Samo Diatta and Remigious Ozioko and
                  Sharon Xu and Axel Jantsch },
  title = {An {LSTM}-based Downscaling Framework for {Australian}
                  Precipitation Projections },
  key = {eml,cdl},
  booktitle = {NeurIPS 2023 Workshop: Tackling Climate Change with
                  Machine Learning at the Conference on Neural
                  Information Processing Systems },
  year = 2023,
  address = {December},
  url = {http://jantsch.se/AxelJantsch/papers/2023/MatthiasBittner-CCAI-NeurIPS.pdf}
}
@inproceedings{bittner:2023a,
  author = {Matthias Bittner and Daniel Hauer and Christian
                  Stippel and Katharina Scheucher and Robin Sudhoff
                  and Axel Jantsch },
  title = {Forecasting Critical Overloads based on
                  Heterogeneous Smart Grid Simulation },
  key = {eml,cdl},
  booktitle = { Proceedings of the International Conference on
                  Machine Learning and Applications (ICMLA},
  year = 2023,
  month = {December},
  address = {Jacksonville, Florida, USA},
  organization = {IEEE and AMLA},
  url = {http://jantsch.se/AxelJantsch/papers/2023/MatthiasBittner-ICMLA.pdf}
}
@inproceedings{schnoell:2023a,
  author = {Daniel Schn\"{o}ll and Matthias Wess and Matthias Bittner and Maximilian G\"{o}tzinger and Axel Jantsch },
  title = {Fast, Quantization Aware {DNN} Training for Efficient {HW} Implementation},
  key = {cdl,ict,eml},
  booktitle = { Proceedings of the 26th Euromicro Conference on Digital System Design (DSD)},
  year = 2023,
  month = {September},
  address = {Durres, Albania},
  url = {http://jantsch.se/AxelJantsch/papers/2023/DanielSchnoell-DSD.pdf}
}
@inproceedings{breuss:2023a,
  author = {David Breuss and Maximilian G\"{o}tzinger and Jenny Vuong and Clemens Reisner and Axel Jantsch },
  title = { {VADAR:} A Vision-based Anomaly Detection Algorithm for Railroads},
  key = {cdl,ict,eml},
  booktitle = {Proceedings of the 26th Euromicro Conference on
                  Digital System Design (DSD)},
  year = 2023,
  month = {September},
  address = {Durres, Albania},
  url = {http://jantsch.se/AxelJantsch/papers/2023/DavidBreuss-DSD.pdf}
}
@inproceedings{wess:2023a,
  author = {Matthias Wess and Dominik Dallinger and Daniel
                  Schn\"{o}ll and Matthias Bittner and Maximilian
                  G\"{o}tzinger and Axel Jantsch },
  title = {Energy Profiling of {DNN} Accelerators},
  key = {cdl,ict,eml},
  booktitle = {Proceedings of the 26th Euromicro Conference on
                  Digital System Design (DSD)},
  year = 2023,
  month = {September},
  address = {Durres, Albania},
  url = {http://jantsch.se/AxelJantsch/papers/2023/MatthiasWess-DSD.pdf}
}
@inproceedings{saqib:2025a,
  author = {Eiraj Saqib and  Oscar Berg and Isaac Leal and Irida
                  Shallari and Axel Jantsch and Silvia Krug and Mattias O’Nils},
  title = {Efficient Edge Inference via Entropy and
                  Magnitude-Aware Feature Map Pruning in Partitioned {CNNs} },
  key = {eml},
  booktitle = { Proceedings of the International Conference on
                  Machine Learning (ICML) },
  year = 2025,
  address = {Vancouver, Canada},
  doi = {10.1109/ICMLA66185.2025.00156},
  url = {http://jantsch.se/AxelJantsch/papers/2025/EirajSaqib-ICML.pdf}
}
@inproceedings{saqib:2023a,
  author = { Eiraj Saqib and Isaac S\'{a}nchez Leal and Irida
                  Shallari and Axel Jantsch and Silvia Krug and
                  Mattias O'Nils },
  title = { Optimizing the {IoT} Performance: A Case Study on
                  Pruning a Distributed {CNN} },
  booktitle = {Proceedings of the IEEE Sensors Applications Symposium (SAS) },
  year = 2023,
  key = {eml},
  url = {http://jantsch.se/AxelJantsch/papers/2023/EirajSaqib-SAS.pdf}
}
@inproceedings{leal:2023a,
  author = { Isaac S\'{a}nchez Leal and Eiraj Saqib and Irida Shallari and
                  Axel Jantsch and Silvia Krug and Mattias O'Nils },
  title = {Waist Tightening of {CNNs}: A Case study on Tiny YOLOv3 for Distributed IoT Implementations},
  key = {eml},
  booktitle = {Proceedings of the Real-time And intelliGent Edge
                  computing workshop (RAGE) },
  year = 2023,
  month = {May},
  address = {San Antonio, Texas},
  url = {http://jantsch.se/AxelJantsch/papers/2023/IsaacSanchezLeal-RAGE.pdf
                  }
}
@inproceedings{kotrba:2023a,
  author = {Thomas Kotrba and Martin Lechner and Omair Sarwar
                  and Axel Jantsch },
  title = {Multispectral Feature Fusion for Deep Object
                  Detection on Embedded {Nvidia} Platforms },
  key = {cdl,ict,eml},
  booktitle = { Design, Automation {\&} Test in Europe Conference
                  {\&} Exhibition ({DATE}) },
  year = 2023,
  month = {April},
  address = {Antwerp, Belgium},
  url = {http://jantsch.se/AxelJantsch/papers/2023/ThomasKotrba-DATE.pdf}
}
@article{lundstroem:2022a,
  author = {Lundstr\"om, Adam and O'Nils, Mattias and Qureshi,
                  Faisal and Jantsch, Axel},
  journal = {IEEE Access},
  title = {Improving deep learning based anomaly detection on
                  multivariate time series through separated anomaly
                  scoring},
  year = 2022,
  pages = {1-1},
  key = {eml},
  doi = {10.1109/ACCESS.2022.3213038}
}
@article{mozelli:2021a,
  author = {Amid Mozelli and Nima Taherinejad and Axel Jantsch},
  title = {A Study on Confidence: an Unsupervised Multi-Agent
                  Machine Learning Experiment },
  journal = {IEEE Design \& Test of Computers },
  year = 2021,
  key = {eml,cdl,ict,selfaware},
  issn = { 2168-2356 },
  doi = { 10.1109/MDAT.2021.3078341 }
}
@article{leal:2021a,
  author = {Isaac S\'{a}nchez Leal and Irida Shallari and Silvia
                  Krug and Axel Jantsch and Mattias O'Nils },
  title = { Impact of Input Data on Intelligence Partitioning
                  Decisions for {IoT} Smart Camera Nodes },
  journal = { Electronics },
  year = 2021,
  volume = 10,
  number = 16,
  key = {eml},
  annote = { SCIE indexed },
  issn = { 2079-9292 },
  doi = {10.3390/electronics10161898},
  url = {http://jantsch.se/AxelJantsch/papers/2021/IsaacLeal-MDPIElectronics.pdf}
}
@article{shallari:2021a,
  author = {Shallari, Irida and S\'{a}nchez Leal, Isaac and Krug,
                  Silvia and Jantsch, Axel and O'Nils, Mattias},
  journal = {IEEE Access},
  title = {{Design space exploration on IoT node: Trade-offs in
                  processing and communication}},
  year = 2021,
  key = {eml},
  doi = {10.1109/ACCESS.2021.3074875},
  url = {http://jantsch.se/AxelJantsch/papers/2021/IridaShallari-IEEEAccess.pdf},
  issn = {2169-3536}
}
@article{lechner:2025a,
  author = {Martin Lechner and Axel Jantsch},
  title = { Hardware-Aware Pruning for Efficient Inference on
                  Embedded Devices },
  journal = { IEEE Access },
  volume = 13,
  key = {eml,cdl,ict},
  doi = {10.1109/ACCESS.2025.3628133},
  url = {http://jantsch.se/AxelJantsch/papers/2025/MartinLechner-HWPruning-IEEEAccess.pdf
                  },
  year = 2025
}
@inproceedings{lechner:2022a,
  author = {Martin Lechner and Axel Jantsch and Lukas Steindl},
  title = {Study of {DNN}-based Ragweed Detection from Drones},
  key = {eml,cdl,ict},
  booktitle = {Proceedings of International Conference on Embedded
                  Computer Systems: Architectures, Modeling and
                  Simulation (SAMOS)},
  year = 2022,
  month = {July},
  address = {Samos, Greece},
  url = {http://jantsch.se/AxelJantsch/papers/2022/MartinLechner-SAMOS.pdf}
}
@inproceedings{haas:2021a,
  author = { Bernhard Haas and Alexander Wendt and Axel Jantsch
                  and Matthias Wess },
  title = {Neural Network Compression Through Shunt Connections
                  and Knowledge Distillation for Semantic Segmentation
                  Problems },
  key = {eml,cdl,ict},
  booktitle = {17th International Conference on Artificial
                  Intelligence Applications and Innovations (AIAI)},
  month = {June},
  doi = {https://doi.org/10.1007/978-3-030-79150-6},
  year = 2021,
  url = {https://link.springer.com/chapter/10.1007/978-3-030-79150-6_28}
}
@article{lechner:2021a,
  author = {Martin Lechner and Axel Jantsch},
  title = {Blackthorn: Latency Estimation Framework for {CNNs}
                  on Embedded {Nvidia} Platforms},
  journal = {IEEE Access},
  year = 2021,
  key = {eml,cdl,ict},
  doi = {10.1109/ACCESS.2021.3101936},
  url = {http://jantsch.se/AxelJantsch/papers/2021/MartinLechner-IEEEAccess.pdf}
}
@article{wess:2024a,
  author = {Wess, Matthias and Schn\"{o}ll, Daniel and
                  Dallinger, Dominik and Bittner, Matthias and
                  Jantsch, Axel},
  title = {Conformal Prediction based Confidence for Latency
                  Estimation of {DNN} Accelerators: A Black-box
                  Approach },
  journal = {IEEE Access},
  issn = {2169-3536},
  key = {eml,cdl,ict},
  year = 2024,
  doi = {10.1109/ACCESS.2024.3439850},
  url = {http://jantsch.se/AxelJantsch/papers/2024/MatthiasWess-IEEEAccess2024-final.pdf}
}
@article{wess:2021a,
  author = {Matthias Wess and Marco Ivanov and Christian Unger and
                  Anvesh Nookala and Alexander Wendt and Axel Jantsch},
  journal = {IEEE Access},
  title = {{ANNETTE}: Accurate Neural Network Execution Time
                  Estimation With Stacked Models},
  year = 2021,
  volume = 9,
  pages = {3545-3556},
  key = {eml,cdl,ict},
  abstract = {With new accelerator hardware for Deep Neural
                  Networks (DNNs), the computing power for Artificial
                  Intelligence (AI) applications has increased
                  rapidly. However, as DNN algorithms become more
                  complex and optimized for specific applications,
                  latency requirements remain challenging, and it is
                  critical to find the optimal points in the design
                  space. To decouple the architectural search from the
                  target hardware, we propose a time estimation
                  framework that allows for modeling the inference
                  latency of DNNs on hardware accelerators based on
                  mapping and layer-wise estimation models. The
                  proposed methodology extracts a set of models from
                  micro-kernel and multi-layer benchmarks and
                  generates a stacked model for mapping and network
                  execution time estimation. We compare estimation
                  accuracy and fidelity of the generated mixed models,
                  statistical models with the roofline model, and a
                  refined roofline model for evaluation. We test the
                  mixed models on the ZCU102 SoC board with Xilinx
                  Deep Neural Network Development Kit (DNNDK) and
                  Intel Neural Compute Stick 2 (NCS2) on a set of 12
                  state-of-the-art neural networks. It shows an
                  average estimation error of 3.47\% for the DNNDK and
                  7.44\% for the NCS2, outperforming the statistical
                  and analytical layer models for almost all selected
                  networks. For a randomly selected subset of 34
                  networks of the NASBench dataset, the mixed model
                  reaches fidelity of 0.988 in Spearman’s $\rho $ rank
                  correlation coefficient metric.},
  doi = {10.1109/ACCESS.2020.3047259},
  url = {http://jantsch.se/AxelJantsch/papers/2021/MatthiasWess-IEEEAccess.pdf},
  issn = {2169-3536}
}
@inproceedings{colucci:2021a,
  author = {Alessio Colucci and D\'avid Juh\'asz and Martin Mosbeck
                  and Alberto Marchisio and Semeen Rehman and Manfred
                  Kreutzer and G\"{u}nter Nadbath and Axel Jantsch and
                  Muhammad Shafique },
  title = { {MLComp}: A Methodology for Machine Learning-based
                  Performance Estimation and Adaptive Selection of
                  {Pareto}-Optimal Compiler Optimization Sequences },
  key = {eml},
  booktitle = {Proceedings of the Design, Automation and Test in Europe Conference and Exhibition },
  year = 2021,
  month = {March},
  url = {http://jantsch.se/AxelJantsch/papers/2021/DavidJuhasz-DATE.pdf}
}
@article{taherinejad:2020a,
  author = {Nima TaheriNejad and Andreas Herkersdorf and
                  Axel Jantsch},
  journal = {IEEE Design Test},
  title = {Autonomous Systems, Trust and Guarantees},
  year = 2020,
  issn = {2168-2356},
  doi = { 10.1109/MDAT.2020.3024145},
  url = {http://jantsch.se/AxelJantsch/papers/2020/NimaTaherinejad-DesignAndTest.pdf},
  key = {selfaware,eml,cdl,ict},
  pages = {1-1}
}
@incollection{wendt:2023a,
  author = { Alexander Wendt and Horst Possegger and Matthias
                  Bittner and Daniel Schn\"{o}ll and Matthias Wess and
                  Du\v{s}an Mali\'{c} and Horst Bischof and Axel
                  Jantsch },
  title = { A Pedestrian Detection Case Study for a Traffic
                  Light Controller },
  booktitle = { Embedded Machine Learning for Cyber-Physical, IoT,
                  and Edge Computing - Software Optimizations and
                  Hardware/Software Codesign },
  key = {eml,cdl,ict},
  publisher = {Springer},
  year = 2023,
  editor = {Sudeep Pasricha and Muhammad Shafique},
  pages = {75--96},
  doi = {10.1007/978-3-031-39932-9},
  url = {https://link.springer.com/chapter/10.1007/978-3-031-39932-9_4}
}
@article{hoffmann:2020a,
  author = {Henrik Hoffmann and Axel Jantsch and Nikil
                  Dutt},
  journal = {Proceedings of the IEEE},
  title = {Embodied Self-Aware Computing Systems},
  year = 2020,
  pages = {1-20},
  key = {selfaware,eml,cdl,ict},
  doi = {10.1109/JPROC.2020.2977054},
  issn = {1558-2256},
  url = {http://jantsch.se/AxelJantsch/papers/2020/HankHoffmann-IEEEProceedings.pdf}
}
@inproceedings{lechner:2019a,
  author = {Martin {Lechner} and Axel {Jantsch} and Sai
                  M. P. {Dinakarrao}},
  booktitle = {2019 Tenth International Green and Sustainable
                  Computing Conference (IGSC)},
  title = {{ResCoNN}: Resource-Efficient {FPGA}-Accelerated
                  {CNN} for Traffic Sign Classification},
  year = 2019,
  pages = {1-6},
  key = {eml},
  doi = {10.1109/IGSC48788.2019.8957186},
  issn = {null},
  month = {Oct}
}
@inproceedings{wendt:2020a,
  author = { David Bechtold and Alexander Wendt and Axel Jantsch },
  title = {Evaluation of Reinforcement Learning Methods for a Self-learning System},
  booktitle = {Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020)},
  year = 2020,
  volume = 2,
  month = {February},
  address = {Valletta, Malta},
  key = {selfaware,eml},
  url = {http://jantsch.se/AxelJantsch/papers/2020/AlexWendt-SelfLearningAgent-ICAART.pdf
}
}
@article{bellman:2020a,
  author = {Kerstin Bellman and Nikil Dutt and Lukas Esterle and
                  Andreas Herkersdorf and Axel Jantsch and C. Landauer
                  and P. R. Lewis and M. Platzner and N. TaheriNejad
                  and K. Tammem\"{a}e},
  journal = {ACM Transactions on Cyber-Physical Systems},
  title = {Self-aware Cyber-Physical Systems},
  year = 2020,
  key = {selfaware,eml,cdl,ict},
  pages = {1-24},
  address = {New York, NY, USA},
  volume = {4},
  number = {4},
  issn = {2378-962X},
  url = {http://jantsch.se/AxelJantsch/papers/2020/KirstinBellmann-TCPS.pdf},
  doi = {10.1145/3375716},
  abstract = {In this article, we make the case for the new class
                  of Self-aware Cyber-physical Systems. By bringing
                  together the two established fields of
                  cyber-physical systems and self-aware computing, we
                  aim at creating systems with strongly increased yet
                  managed autonomy, which is a main requirement for
                  many emerging and future applications and
                  technologies. Self-aware cyber-physical systems are
                  situated in a physical environment and constrained
                  in their resources, and they understand their own
                  state and environment and, based on that
                  understanding, are able to make decisions
                  autonomously at runtime in a self-explanatory
                  way. In an attempt to lay out a research agenda, we
                  bring up and elaborate on five key challenges for
                  future self-aware cyber-physical systems: (i) How
                  can we build resource-sensitive yet self-aware
                  systems? (ii) How to acknowledge situatedness and
                  subjectivity? (iii) What are effective
                  infrastructures for implementing self-awareness
                  processes? (iv) How can we verify self-aware
                  cyber-physical systems and, in particular, which
                  guarantees can we give? (v) What novel development
                  processes will be required to engineer self-aware
                  cyber-physical systems? We review each of these
                  challenges in some detail and emphasize that
                  addressing all of them requires the system to make a
                  comprehensive assessment of the situation and a
                  continual introspection of its own state to sensibly
                  balance diverse requirements, constraints,
                  short-term and long-term objectives. Throughout, we
                  draw on three examples of cyber-physical systems
                  that may benefit from self-awareness: a
                  multi-processor system-on-chip, a Mars rover, and an
                  implanted insulin pump. These three very different
                  systems nevertheless have similar characteristics:
                  limited resources, complex unforeseeable
                  environmental dynamics, high expectations on their
                  reliability, and substantial levels of risk
                  associated with malfunctioning. Using these
                  examples, we discuss the potential role of
                  self-awareness in both highly complex and rather
                  more simple systems, and as a main conclusion we
                  highlight the need for research on above listed
                  topics.},
  month = {June},
  articleno = {38},
  numpages = {26}
}
@inproceedings{hanif:2019a,
  author = {Muhammad Abdullah Hanif and Muhammad Zuhaib Akbar
                  and Rehan Ahmed and Semeen Rehman and Axel Jantsch
                  and Muhammad Shafique },
  title = {{MemGANs}: Memory Management for Energy-Efficient
                  Acceleration of Complex Computations in Hardware
                  Architectures for Generative Adversarial Networks},
  key = {eml},
  booktitle = { Proceesings of the International Symposium on Low
                  Power Electronics and Design (ISLPED) },
  year = 2019,
  month = {July},
  address = {Lausanne, Switzerland},
  url = {http://jantsch.se/AxelJantsch/papers/2019/AbdullaHanif-ISLPED.pdf}
}
@inproceedings{taherinejad:2019a,
  author = {Nima TaheriNejad and Axel Jantsch},
  title = {Improved Machine Learning using Confidence},
  key = {selfaware,eml},
  booktitle = {IEEE Canadian Conference of Electrical and Computer
                  Engineering (CCECE)},
  year = 2019,
  month = {May},
  address = {Edmonton, Canada},
  url = {http://jantsch.se/AxelJantsch/papers/2019/NimaTaherinejad-CCECE.pdf}
}
@article{pagani:2018a,
  author = {Santiago Pagani and Sai Manoj P D and Axel Jantsch
                  and J\"org Henkel},
  title = {Machine Learning for Power, Energy, and Thermal
                  Management on Multi-core Processors: A Survey},
  journal = {IEEE Transaction on Computer Aided Design (TCAD)},
  year = 2018,
  key = {eml,survey},
  tudatabase = 1,
  url = {http://jantsch.se/AxelJantsch/papers/2018/SantiagoPagani-TCAD-PowerManagementSurvey.pdf},
  doi = {10.1109/TCAD.2018.2878168},
  issn = {0278-0070}
}
@article{wess:2018a,
  author = { Matthias Wess and Sai Manoj Pudukotai Dinakarrao
                  and Axel Jantsch},
  title = {Weighted Quantization-Regularization in {DNNs} for
                  Weight Memory Minimization towards {HW}
                  Implementation },
  journal = {IEEE Transactions on Computer-Aided Design of
                  Integrated Circuits and Systems },
  year = 2018,
  volume = 37,
  number = 10,
  month = {October},
  key = {eml},
  issn = {0278-0070},
  doi = {10.1109/TCAD.2018.2857080},
  tudatabase = 1,
  url = {http://jantsch.se/AxelJantsch/papers/2018/MatthiasWess-CODES.pdf}
}