Neuromorphic Sensing and Computing Systems

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Circuit and Signal Processing".

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 20769

Special Issue Editors

Ultra Low Power Systems for IoT, Stichting IMEC Nederland, Eindhoven, The Netherlands
Interests: neuromorphic engineering; bio-signal processing; neuroscience; on-line learning; edge computing; embedded systems
Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA
Interests: computer architectures; neuromorphic computing; in-memory computing; non-volatile memories

Special Issue Information

Dear Colleagues,

Neuromorphic computing is currently being proposed as an alternative and efficient way to carry out computation using principles derived from neuro-biological systems. Although the neuromorphic term has historically been used to describe hardware implementations of neural circuits in analog, digital, or mixed-mode analog/digital VLSI, in recent years, it has also been used to describe a wider spectrum of sensing and computing systems. These systems sometimes include emerging memories, and alternative neuron and synapse technologies. In all cases, the application of neuromorphic systems faces the challenge of building novel algorithms, tools, and architectures that can best cope with the nature of low-power, dense, and parallel elements. The complexity and sophistication of such systems is increasing over time with an unprecedented speed both at the theoretical and technological level.

Thus, in this Special Issue, we aim to start a discussion about the state of the art in neuromorphic sensing and computing systems, analyzing architectures, algorithms, and their potential impact in a broad spectrum of applications.

For this purpose, this Special Issue is open to receiving a variety of meaningful and valuable manuscripts concerning the topic of neuromorphic sensing and computing systems. We welcome work related to hardware architectures, event-based sensing and computing, spiking neural networks, learning systems, and alternative neuromorphic computing paradigms. We will also consider submissions that involve emerging memories and unconventional computing technologies as candidate solutions for the execution of neural information processing in an extremely efficient way.

Dr. Federico Corradi
Dr. Anup Das
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Analog/digital/mixed-signal circuits and architectures for neuromorphic systems
  • Architectures and algorithms for neuromorphic computing
  • Spiking neural networks
  • Bio-inspired signal processing
  • Neuro mimicking materials and principles
  • Event-based sensory systems, spike-based processing
  • On-line, real-time, edge computing
  • Learning systems
  • High performance neuromorphic computing systems and architectures
  • Spintronics, memristors, carbon nanotubes, photonics

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

22 pages, 4778 KiB  
Article
Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants
by Ankita Paul, Md. Abu Saleh Tajin, Anup Das, William M. Mongan and Kapil R. Dandekar
Electronics 2022, 11(5), 682; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11050682 - 23 Feb 2022
Cited by 8 | Viewed by 2461
Abstract
Precise monitoring of respiratory rate in premature newborn infants is essential to initiating medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a deep-learning-enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted [...] Read more.
Precise monitoring of respiratory rate in premature newborn infants is essential to initiating medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a deep-learning-enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on the infant’s body. We propose a five-stage design pipeline involving data collection and labeling, feature scaling, deep learning model selection with hyperparameter tuning, model training and validation, and model testing and deployment. The model used is a 1-D convolutional neural network (1DCNN) architecture with one convolution layer, one pooling layer, and three fully-connected layers, achieving 97.15% classification accuracy. To address the energy limitations of wearable processing, several quantization techniques are explored, and their performance and energy consumption are analyzed for the respiratory classification task. Results demonstrate a reduction of energy footprints and model storage overhead with a considerable degradation of the classification accuracy, meaning that quantization and other model compression techniques are not the best solution for respiratory classification problem on wearable devices. To improve accuracy while reducing the energy consumption, we propose a novel spiking neural network (SNN)-based respiratory classification solution, which can be implemented on event-driven neuromorphic hardware platforms. To this end, we propose an approach to convert the analog operations of our baseline trained 1DCNN to their spiking equivalent. We perform a design-space exploration using the parameters of the converted SNN to generate inference solutions having different accuracy and energy footprints. We select a solution that achieves an accuracy of 93.33% with 18x lower energy compared to the baseline 1DCNN model. Additionally, the proposed SNN solution achieves similar accuracy as the quantized model with a 4× lower energy. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Figure 1

16 pages, 6868 KiB  
Article
A Low-Cost Hardware-Friendly Spiking Neural Network Based on Binary MRAM Synapses, Accelerated Using In-Memory Computing
by Yihao Wang, Danqing Wu, Yu Wang, Xianwu Hu, Zizhao Ma, Jiayun Feng and Yufeng Xie
Electronics 2021, 10(19), 2441; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics10192441 - 08 Oct 2021
Cited by 5 | Viewed by 2102
Abstract
In recent years, the scaling down that Moore’s Law relies on has been gradually slowing down, and the traditional von Neumann architecture has been limiting the improvement of computing power. Thus, neuromorphic in-memory computing hardware has been proposed and is becoming a promising [...] Read more.
In recent years, the scaling down that Moore’s Law relies on has been gradually slowing down, and the traditional von Neumann architecture has been limiting the improvement of computing power. Thus, neuromorphic in-memory computing hardware has been proposed and is becoming a promising alternative. However, there is still a long way to make it possible, and one of the problems is to provide an efficient, reliable, and achievable neural network for hardware implementation. In this paper, we proposed a two-layer fully connected spiking neural network based on binary MRAM (Magneto-resistive Random Access Memory) synapses with low hardware cost. First, the network used an array of multiple binary MRAM cells to store multi-bit fixed-point weight values. This helps to simplify the read/write circuit. Second, we used different kinds of spike encoders that ensure the sparsity of input spikes, to reduce the complexity of peripheral circuits, such as sense amplifiers. Third, we designed a single-step learning rule, which fit well with the fixed-point binary weights. Fourth, we replaced the traditional exponential Leak-Integrate-Fire (LIF) neuron model to avoid the massive cost of exponential circuits. The simulation results showed that, compared to other similar works, our SNN with 1184 neurons and 313,600 synapses achieved an accuracy of up to 90.6% in the MNIST recognition task with full-resolution (28 × 28) and full-bit-depth (8-bit) images. In the case of low-resolution (16 × 16) and black-white (1-bit) images, the smaller version of our network with 384 neurons and 32,768 synapses still maintained an accuracy of about 77%, extending its application to ultra-low-cost situations. Both versions need less than 30,000 samples to reach convergence, which is a >50% reduction compared to other similar networks. As for robustness, it is immune to the fluctuation of MRAM cell resistance. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Figure 1

19 pages, 1732 KiB  
Article
EDHA: Event-Driven High Accurate Simulator for Spike Neural Networks
by Lingfei Mo, Xinao Chen and Gang Wang
Electronics 2021, 10(18), 2281; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics10182281 - 17 Sep 2021
Cited by 2 | Viewed by 2620
Abstract
In recent years, spiking neural networks (SNNs) have attracted increasingly more researchers to study by virtue of its bio-interpretability and low-power computing. The SNN simulator is an essential tool to accomplish image classification, recognition, speech recognition, and other tasks using SNN. However, most [...] Read more.
In recent years, spiking neural networks (SNNs) have attracted increasingly more researchers to study by virtue of its bio-interpretability and low-power computing. The SNN simulator is an essential tool to accomplish image classification, recognition, speech recognition, and other tasks using SNN. However, most of the existing simulators for spike neural networks are clock-driven, which has two main problems. First, the calculation result is affected by time slice, which obviously shows that when the calculation accuracy is low, the calculation speed is fast, but when the calculation accuracy is high, the calculation speed is unacceptable. The other is the failure of lateral inhibition, which severely affects SNN learning. In order to solve these problems, an event-driven high accurate simulator named EDHA (Event-Driven High Accuracy) for spike neural networks is proposed in this paper. EDHA takes full advantage of the event-driven characteristics of SNN and only calculates when a spike is generated, which is independent of the time slice. Compared with previous SNN simulators, EDHA is completely event-driven, which reduces a large amount of calculations and achieves higher computational accuracy. The calculation speed of EDHA in the MNIST classification task is more than 10 times faster than that of mainstream clock-driven simulators. By optimizing the spike encoding method, the former can even achieve more than 100 times faster than the latter. Due to the cross-platform characteristics of Java, EDHA can run on x86, amd64, ARM, and other platforms that support Java. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Graphical abstract

19 pages, 1382 KiB  
Article
LogicSNN: A Unified Spiking Neural Networks Logical Operation Paradigm
by Lingfei Mo and Minghao Wang
Electronics 2021, 10(17), 2123; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics10172123 - 31 Aug 2021
Cited by 5 | Viewed by 2758
Abstract
LogicSNN, a unified spiking neural networks (SNN) logical operation paradigm is proposed in this paper. First, we define the logical variables under the semantics of SNN. Then, we design the network structure of this paradigm and use spike-timing-dependent plasticity for training. According to [...] Read more.
LogicSNN, a unified spiking neural networks (SNN) logical operation paradigm is proposed in this paper. First, we define the logical variables under the semantics of SNN. Then, we design the network structure of this paradigm and use spike-timing-dependent plasticity for training. According to this paradigm, six kinds of basic SNN binary logical operation modules and three kinds of combined logical networks based on these basic modules are implemented. Through these experiments, the rationality, cascading characteristics and the potential of building large-scale network of this paradigm are verified. This study fills in the blanks of the logical operation of SNN and provides a possible way to realize more complex machine learning capabilities. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Figure 1

20 pages, 2136 KiB  
Article
Radar-Based Hand Gesture Recognition Using Spiking Neural Networks
by Ing Jyh Tsang, Federico Corradi, Manolis Sifalakis, Werner Van Leekwijck and Steven Latré
Electronics 2021, 10(12), 1405; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics10121405 - 11 Jun 2021
Cited by 22 | Viewed by 5110
Abstract
We propose a spiking neural network (SNN) approach for radar-based hand gesture recognition (HGR), using frequency modulated continuous wave (FMCW) millimeter-wave radar. After pre-processing the range-Doppler or micro-Doppler radar signal, we use a signal-to-spike conversion scheme that encodes radar Doppler maps into spike [...] Read more.
We propose a spiking neural network (SNN) approach for radar-based hand gesture recognition (HGR), using frequency modulated continuous wave (FMCW) millimeter-wave radar. After pre-processing the range-Doppler or micro-Doppler radar signal, we use a signal-to-spike conversion scheme that encodes radar Doppler maps into spike trains. The spike trains are fed into a spiking recurrent neural network, a liquid state machine (LSM). The readout spike signal from the SNN is then used as input for different classifiers for comparison, including logistic regression, random forest, and support vector machine (SVM). Using liquid state machines of less than 1000 neurons, we achieve better than state-of-the-art results on two publicly available reference datasets, reaching over 98% accuracy on 10-fold cross-validation for both data sets. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Figure 1

Review

Jump to: Research

24 pages, 1517 KiB  
Review
Nonvolatile Memories in Spiking Neural Network Architectures: Current and Emerging Trends
by M. Lakshmi Varshika, Federico Corradi and Anup Das
Electronics 2022, 11(10), 1610; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11101610 - 18 May 2022
Cited by 6 | Viewed by 3251
Abstract
A sustainable computing scenario demands more energy-efficient processors. Neuromorphic systems mimic biological functions by employing spiking neural networks for achieving brain-like efficiency, speed, adaptability, and intelligence. Current trends in neuromorphic technologies address the challenges of investigating novel materials, systems, and architectures for enabling [...] Read more.
A sustainable computing scenario demands more energy-efficient processors. Neuromorphic systems mimic biological functions by employing spiking neural networks for achieving brain-like efficiency, speed, adaptability, and intelligence. Current trends in neuromorphic technologies address the challenges of investigating novel materials, systems, and architectures for enabling high-integration and extreme low-power brain-inspired computing. This review collects the most recent trends in exploiting the physical properties of nonvolatile memory technologies for implementing efficient in-memory and in-device computing with spike-based neuromorphic architectures. Full article
(This article belongs to the Special Issue Neuromorphic Sensing and Computing Systems)
Show Figures

Figure 1

Back to TopTop