@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -q -ob publ-ML.bib --remove keywords -c 'key : "ML"' /home/jantsch/Website/}}
@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -q -oc /home/jantsch/Website/ -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" )))
	    or $key = "hauer:2021a"
	    ' /home/jantsch/text/papers/lit.bib}}
@comment{{Example entry for online references:
  title = MS Windows NT Kernel Description,
  howpublished = \url,
  note = Accessed: 2010-09-30
  title =	 Quine-McCluskey Algorithm,
  author =  Wikipedia ,
  year = 2021,
  howpublished =
  note =	 Accessed: 2021-08-11
  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
  year = 2022,
  pages = {1-1},
  key = { eml },
  doi = {10.1109/ACCESS.2022.3213038}
  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,selfaware},
  issn = { 2168-2356 },
  doi = { 10.1109/MDAT.2021.3078341 }
  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 = {}
  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 = {},
  issn = {2169-3536}
  author = {Martin Lechner and Axel Jantsch and Lukas Steindl},
  title = {Study of {DNN}-based Ragweed Detection from Drones},
  key = {eml,cdl},
  booktitle = {Proceedings of International Conference on Embedded
                  Computer Systems: Architectures, Modeling and
                  Simulation (SAMOS)},
  year = 2022,
  month = {July},
  address = {Samos, Greece},
  url = {}
  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},
  booktitle = {17th International Conference on Artificial
                  Intelligence Applications and Innovations (AIAI)},
  month = {June},
  doi = {},
  year = 2021
  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},
  doi = {10.1109/ACCESS.2021.3101936},
  url = {}
  author = {M. {Wess} and M. {Ivanov} and C. {Unger} and
                  A. {Nookala} and A. {Wendt} and A. {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},
  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 = {},
  issn = {2169-3536}
  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 = {}
  author = {N. {TaheriNejad} and A. {Herkersdorf} and
                  A. {Jantsch}},
  journal = {IEEE Design Test},
  title = {Autonomous Systems, Trust and Guarantees},
  year = 2020,
  issn = {2168-2356},
  doi = { 10.1109/MDAT.2020.3024145},
  url = {},
  key = {selfaware,eml,cdl},
  pages = {1-1}
  author = {Henrik {Hoffmann} and Axel {Jantsch} and Nikil
                  D. {Dutt}},
  journal = {Proceedings of the IEEE},
  title = {Embodied Self-Aware Computing Systems},
  year = 2020,
  pages = {1-20},
  key = {selfaware,eml,cdl},
  doi = {10.1109/JPROC.2020.2977054},
  issn = {1558-2256},
  url = {}
  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 = {ml},
  doi = {10.1109/IGSC48788.2019.8957186},
  issn = {null},
  month = {Oct}
  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,ml},
  url = {
  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},
  pages = {1-24},
  address = {New York, NY, USA},
  volume = {4},
  number = {4},
  issn = {2378-962X},
  url = {},
  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
  month = {June},
  articleno = {38},
  numpages = {26}
  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 = {ml},
  booktitle = { Proceesings of the International Symposium on Low
                  Power Electronics and Design (ISLPED) },
  year = 2019,
  month = {July},
  address = {Lausanne, Switzerland},
  url = {}
  author = {Nima TaheriNejad and Axel Jantsch},
  title = {Improved Machine Learning using Confidence},
  key = {selfaware,ml},
  booktitle = {IEEE Canadian Conference of Electrical and Computer
                  Engineering (CCECE)},
  year = 2019,
  month = {May},
  address = {Edmonton, Canada},
  url = {}
  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 = {ml,survey},
  tudatabase = 1,
  url = {},
  doi = {10.1109/TCAD.2018.2878168},
  issn = {0278-0070}
  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 = {ml},
  issn = {0278-0070},
  doi = {10.1109/TCAD.2018.2857080},
  tudatabase = 1,
  url = {}