Article
Nanoscience & Nanotechnology
Chang Liu, Yanghao Wang, Teng Zhang, Rui Yuan, Yuchao Yang
Summary: Neuromorphic computing aims to connect cognitive behaviors with efficient computing systems in a biologically inspired way. Attention mechanism, an important cognitive behavior for filtering and regulating spatio-temporal information, can be efficiently processed using the dynamic capabilities of emerging neuromorphic devices. A basic top-down attention computing component comprising a synaptic transistor and a neuron is proposed and demonstrated to effectively filter and control information. The component exhibits new dynamic circuit behaviors, such as conductance oscillation and activate function switching, offering a power and area-saving method for constructing complex neuromorphic systems.
ADVANCED ELECTRONIC MATERIALS
(2023)
Article
Engineering, Electrical & Electronic
Mattia Balutto, Giacomo Ripamonti, Pablo Daniel Antoszczuk, Stefano Michelis, Federico Iob, Alessandro Dago, Stefano Saggini
Summary: In recent years, the power consumption of data centers has increased, leading to a shift in server rack architecture to higher voltage levels. The conventional power delivery system involves two stages of dc-dc conversion, with the 4-to-1 switched tank converter (STC) being commonly used in the first stage. However, the STC generates a large inrush current during startup. This article proposes a novel control technique to mitigate the inrush current and presents a strategy to minimize resonant frequency mismatch in the STC.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2023)
Article
Engineering, Electrical & Electronic
Giacomo Ripamonti, Mario Ursino, Stefano Saggini, Stefano Michelis, Federico Faccio
Summary: This article presents a novel control system for a regulated resonant switched-capacitor point-of-load converter, together with its steady-state and small-signal analyses. The system utilizes a combined frequency/phase shift on-chip controller to regulate the output voltage for a wide range of conversion ratios, while maximizing efficiency through different operation modes. A prototype based on a 130-nm CMOS technology ASIC has been designed, achieving the desired conversion range and high power density with reduced inductor size. The converter efficiency is comparable to that of an integrated buck converter designed for the same application.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2021)
Article
Engineering, Electrical & Electronic
Nathan Miles Ellis, Rajeevan Amirtharajah
Summary: This paper provides a comprehensive review of Dickson-type HSC converters and introduces eight fundamental reduced HSC Dickson structures. It presents analysis and characterization of large signal operating points, capacitor sizing regimes, switching schemes, and maximum allowable power throughput. The analysis is verified through simulation and validated with a hardware prototype.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Materials Science, Multidisciplinary
P. Praveen, K. V. Vijoy, Honey John, K. J. Saji
Summary: Polymer-based memristors are a promising solution for wearable neuromorphic systems due to their low-cost fabrication route and mechanical flexibility. PDMS-graphite composite-based memristors were fabricated and showed bipolar resistive switching and emulated various synaptic behaviors.
Article
Computer Science, Information Systems
Md Reyaz Hussan, Adil Sarwar, Irfan Khan, Mohd Tariq, Mohammad Tayyab, Waleed Alhosaini
Summary: This paper introduces an 11-level switched-capacitor multilevel inverter with a 2.5 times boosting feature, detailing its topology and operation principles, and validates its performance through experiments.
Article
Automation & Control Systems
Sze Sing Lee, Kyo-Beum Lee
Summary: A novel topology of multilevel inverters is proposed in this study, which successfully reduces common-mode voltage by connecting the neutral of the ac output to the midpoint of the dc link. All switched-capacitors are ensured to be charged for at least half of the fundamental period, alleviating capacitor voltage ripples and current spikes.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Engineering, Electrical & Electronic
Shouheng Han, Yijie Wang, Zhenli Xie, Yueshi Guan, J. Marcos Alonso, Dianguo Xu
Summary: This letter proposes a switched capacitor-based continuously adjustable modular bidirectional dc-dc converter with three types of modules, achieving a peak efficiency of 97.15% in a prototype.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Tan-Tai Tran, Minh-Khai Nguyen, Truong-Duy Duong, Young-Cheol Lim, Joon-Ho Choi
Summary: This article introduces a new switched-capacitor-based multilevel inverter topology, which is capable of generating efficient output voltage waveform and achieving capacitor balance through direct charging. The article provides details on the operating principles, circuit description, control technique, and component selection of the proposed topology. A comparative study with other topologies, along with simulation and experimental results, is presented to validate the theoretical analysis.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Daniel Augusto Villamizar, Dante Gabriel Muratore, James B. Wieser, Boris Murmann
Summary: This paper introduces a 32-channel analog filterbank for front-end signal processing in sound classification systems, utilizing a passive N-path switched capacitor topology for high power efficiency and reconfigurability. The proposed circuit effectively absorbs unwanted harmonic mixing products using machine learning models and features a computationally efficient circuit model for pre-silicon study. Experimental results demonstrate competitive classification accuracy and reduced energy consumption for feature extraction compared to digital realizations.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2021)
Article
Engineering, Electrical & Electronic
Tapas Roy, Musie Welday Tesfay, Byamakesh Nayak, Chinmoy Kumar Panigrahi
Summary: This brief introduces a novel switched-capacitor multilevel inverter that can produce a 7-level output voltage with lower number of components and more cost-effective than other inverters. A detailed comparison study and experimental validation are presented to illustrate the performance and effectiveness of the proposed inverter.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2021)
Article
Engineering, Electrical & Electronic
Hossein Khoun Jahan, Mitra Sarhangzadeh, Jaber Fallah Ardashir, Frede Blaabjerg
Summary: This article proposes a new inverter unit for grid-tied photovoltaic systems. The compact switched-capacitor-based inverter has several advantages, including mitigating capacitive leakage current, spontaneous voltage balancing, full reactive power transfer, low voltage stress on capacitors, and a symmetric switching sequence.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Jongkil Park, YeonJoo Jeong, Jaewook Kim, Suyoun Lee, Joon Young Kwak, Jong-Keuk Park, Inho Kim
Summary: In this study, a novel neuron implementation model is proposed, which enhances neural and synaptic dynamics using time-embedded floating-point arithmetic for better biological plausibility and low-power consumption. The proposed algorithm enables sharing temporal information with a membrane potential to minimize memory usage and reduce dynamic power consumption.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Engineering, Electrical & Electronic
Shikai Chen, Yuanmao Ye, Shaojun Chen, Teke Hua, Xiaolin Wang
Summary: This article introduces a new type of three-phase boost inverter that uses switched-capacitor (SC) units to supply the traditional three-phase inverting bridge. With a coupled structure and a specific modulation strategy, this inverter has many attractive features. A SC-based multilevel inverter (MLI) with a triple-mode SC unit and varied terminal voltage is developed, resulting in higher boost factor and more output levels compared to existing topologies. Detailed analysis is provided on the topology, working principle, capacitor voltage ripples, power losses, and comparative study. The feasibility and performance are experimentally evaluated with a downscale prototype, achieving an efficiency above 97.6%.
IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
(2023)
Article
Engineering, Electrical & Electronic
Dengke Zheng, Yuhang Yang, Shiming Hu, Yan Deng
Summary: In this article, a method based on q-u curves of capacitors is proposed to accurately calculate capacitor charge-sharing loss, in order to improve the efficiency of switched-capacitor circuits. The output impedance of an SCC with a finite output capacitance can be accurately modeled in medium switching frequency by considering both capacitor charge-sharing loss and conduction loss. Compared to previous modeling techniques, the proposed R-LSL method not only considers the output capacitor effect, but also applies to various well-posed switched-capacitor circuits. Simulations and experiments validate the accuracy of R-LSL in predicting the output impedance with changes in switching frequency, output capacitor, and duty cycle in the mid-band.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2023)
Article
Neurosciences
Chen Liu, Guillaume Bellec, Bernhard Vogginger, David Kappel, Johannes Partzsch, Felix Neumaerker, Sebastian Hoeppner, Wolfgang Maass, Steve B. Furber, Robert Legenstein, Christian G. Mayr
FRONTIERS IN NEUROSCIENCE
(2018)
Article
Neurosciences
Hanna Keren, Johannes Partzsch, Shimon Marom, Christian G. Mayr
FRONTIERS IN NEUROSCIENCE
(2019)
Article
Engineering, Biomedical
Yexin Yan, David Kappel, Felix Neumaerker, Johannes Partzsch, Bernhard Vogginger, Sebastian Hoeppner, Steve Furber, Wolfgang Maass, Robert Legenstein, Christian Mayr
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS
(2019)
Article
Engineering, Electrical & Electronic
Sebastian Hoeppner, Bernhard Vogginger, Yexin Yan, Andreas Dixius, Stefan Scholze, Johannes Partzsch, Felix Neumaerker, Stephan Hartmann, Stefan Schiefer, Georg Ellguth, Love Cederstroem, Luis A. Plana, Jim Garside, Steve Furber, Christian Mayr
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2019)
Article
Computer Science, Information Systems
Johannes Partzsch, Christian Mayr, Massimiliano Giulioni, Marko Noack, Stefan Haenzsche, Stefan Scholze, Sebastian Hoeppner, Paolo Del Giudice, Rene Schueffny
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2020)
Review
Multidisciplinary Sciences
Richard George, Michela Chiappalone, Michele Giugliano, Timothee Levi, Stefano Vassanelli, Johannes Partzsch, Christian Mayr
Article
Computer Science, Hardware & Architecture
Seyed Mohammad Ali Zeinolabedin, Johannes Partzsch, Christian Mayr
IEEE DESIGN & TEST
(2021)
Article
Computer Science, Artificial Intelligence
Eric Mueller, Sebastian Schmitt, Christian Mauch, Sebastian Billaudelle, Andreas Gruebl, Maurice Guettler, Dan Husmann, Joscha Ilmberger, Sebastian Jeltsch, Jakob Kaiser, Johann Klaehn, Mitja Kleider, Christoph Koke, Jose Montes, Paul Mueller, Johannes Partzsch, Felix Passenberg, Hartmut Schmidt, Bernhard Vogginger, Jonas Weidner, Christian Mayr, Johannes Schemmel
Summary: BrainScaleS-1 is a large-scale mixed-signal accelerated neuromorphic system used for computational neuroscience and beyond-von-Neumann computing. The BrainScaleS Operating System (BrainScaleS OS) is the software stack that allows users to emulate networks using the PyNN language with minimal knowledge of the system. The system has been extensively used in various neuromorphic experiments and demonstrates high fault tolerance. The software stack is designed for performance and includes features such as parallel configuration and synchronized experiments.
Proceedings Paper
Computer Science, Artificial Intelligence
Tim Langer, Bernd Waschneck, Johannes Partzsch, Florian Kelber, Christian Mayr
Summary: This study explores the classification of walking direction using ultrasonic signals for entrance counting. Different neural network architectures, machine learning techniques, and classical signal processing techniques are compared. The focus is on developing a hardware-efficient system concept with a single ultrasonic receiver. The study compares different ultrasonic measurement methods and analyzes the system's hardware efficiency. The results show that the proposed hardware-efficient system achieves accurate entrance counting using a single ultrasonic receiver.
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Matthias Jobst, Johannes Partzsch, Chen Liu, Liyuan Guo, Dennis Walter, Saif-Ur Rehman, Stefan Scholze, Sebastian Hoppner, Christian Mayr
Summary: State-of-the-art low-power ECG hardware classifiers rely on extraction of predefined features, which limits their flexibility. In this study, we propose a machine-learning based approach that combines recurrent neural networks and delta encoding to achieve a more flexible and energy-efficient ECG classification in hardware.
2022 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2022): INTELLIGENT TECHNOLOGY IN THE POST-PANDEMIC ERA
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Seyed Mohammad Ali Zeinolabedin, Johannes Partzsch, Christian Mayr
Summary: The paper introduces a hardware architecture for analyzing debug trace stream in real-time, which can monitor memory operations without affecting the normal execution of the system.
PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021)
(2021)
Proceedings Paper
Engineering, Electrical & Electronic
Vasilis Thanasoulis, Bernhard Vogginger, Johannes Partzsch, Christian Mayr
Summary: Neuromorphic engineering offers a promising alternative to numerical simulations for studying spiking neural networks by implementing high integration density synapse-and-neuron blocks. This paper presents a measurement methodology and results of a neural benchmark testing the configurable delays, multicasting, and connectivity of routing logic in neuromorphic hardware. The results demonstrate the suitability of communication and routing logic for delay-based neural computation and highlight the effects of time discretization on pulse timestamp resolution.
2021 28TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS (IEEE ICECS 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Sebastian Schmitt, Johann Klaehn, Guillaume Bellec, Andreas Gruebl, Maurice Guettler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Sebastian Jeltsch, Vitali Karasenko, Mitja Kleider, Christoph Koke, Alexander Kononov, Christian Mauch, Eric Mueller, Paul Mueller, Johannes Partzsch, Mihai A. Petrovici, Stefan Schiefer, Stefan Scholze, Vasilis Thanasoulis, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, Christian Mayr, Rene Schueffny, Johannes Schemmel, Karlheinz Meier
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2017)
Proceedings Paper
Engineering, Electrical & Electronic
M. A. Petrovici, S. Schmitt, J. Klaehn, D. Stoeckel, A. Schroeder, G. Bellec, J. Bill, O. Breitwieser, I. Bytschok, A. Gruebl, M. Guettler, A. Hartel, S. Hartmann, D. Husmann, K. Husmann, S. Jeltsch, V. Karasenko, M. Kleider, C. Koke, A. Kononov, C. Mauch, E. Mueller, P. Mueller, J. Partzsch, T. Pfeil, S. Schiefer, S. Scholze, A. Subramoney, V. Thanasoulis, B. Vogginger, R. Legenstein, W. Maass, R. Schueffny, C. Mayr, J. Schemmel, K. Meier
2017 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS)
(2017)
Proceedings Paper
Engineering, Electrical & Electronic
Sebastian Hoeppner, Yexin Yan, Bernhard Vogginger, Andreas Dixius, Johannes Partzsch, Prateek Joshi, Felix Neumaerker, Stephan Hartmann, Stefan Schiefer, Stefan Scholze, Georg Ellguth, Love Cederstroem, Matthias Eberlein, Christian Mayr, Steve Temple, Luis Plana, Jim Garside, Simon Davison, David R. Lester, Steve Furber
2017 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS)
(2017)