Special Issue "Neuromorphic Sensing and Computing Systems"
Deadline for manuscript submissions: 31 January 2022.
Interests: neuromorphic engineering; bio-signal processing; neuroscience; on-line learning; edge computing; embedded systems
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
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 papers will be 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 1800 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.
- 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
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Planned Paper 1. Direct Spike Encoding Circuit for Audio Signal
Abstract: The lack of spike encoding circuits for audio signals limits the application of neuromorphic computing methods represented by spike neural networks (SNN) in audio signal processing. Four essential
processes are included in the traditional spike encoding circuits for audio signals: acquisition of audio signal, analog to digital conversion, time to frequency domain conversion, and spike encoding. Due to the software calculation circuit for time to frequency domain conversion and spike encoding in traditional spike encoding circuits for audio signals, the traditional method has a certain conversion delay. In addition, the encoding result is highly dependent on the sampling accuracy and speed of the analog to digital converter. This paper proposes DSEC: a direct spike encoding circuit for audio signals, which contains audio signal acquisition, band-pass filtering, and spike encoding. Analog to digital conversion is not contained and all processes in DSEC are completely implemented by hardware circuits, which speeds up the input response significantly.