Research Topic

Recent Advances of Deep Spiking Neural Networks and Neuromorphic Computation for Computer Vision

About this Research Topic

Deep Neural Networks (DNNs) and their applications for computer vision have been actively developed in recent years. Along with them, methods and systems for neuromorphic computation and Spiking Neural Networks (SNNs) in particular are rapidly emerging means of neural information processing, drawing inspiration from brain processes. The prominent background of this Research Topic is that SNNs have the potential to advance technologies and techniques in fields as neuromorphic systems, deep neural networks, computer vision, image and image processing, intelligent surveillance, artificial intelligence, and indeed any fields that involve complex temporal or spatiotemporal data. SNN, as the third generation of neural networks, is able to operate on noisy data, in changing environments at low power with high effectiveness. Due to the biological foundation principles, SNN research outcomes are strongly positioned to benefit from advances made in the fields of evolutionary and cognitive neuroscience. We believe that this area is quickly establishing itself as an effective alternative to traditional machine learning, computational vision, digital imaging, and the research interest in this area is growing rapidly.

This Research Topic aims to bring together research works of contemporary areas of SNNs for computer vision, including theoretical, computational, application-oriented, experimental studies, and emerging technologies in deep neural networks, neuromorphic systems, computer vision, imaging, and video technology.

The subjects related to this Research Topic include, but are not limited to:
• New theories of spike information representation
• Learning algorithms for Deep SNNs
• Theory and analytics of SNNs
• Optimization and analysis of SNNs
• Knowledge transfer between humans and SNN machines
• Theory or practice in biologically realistic neural simulation and biometrics models
• Spike encoding methods for computer vision
• SNN model visualization and visual scene understanding
• SNN models for visual information processing
• Evolving SNN for integrated audio-visual information processing
• SNN for brain-inspired computer vision
• SNN for brain-inspired dynamic imaging
• SNN for brain-inspired video technology
• SNN for brain-inspired image processing and artifact removal
• SNN for brain-inspired time series analysis
• SNN for brain-inspired autonomous vehicles
• SNN for brain-inspired artificial intelligence
• SNN applications in neuroinformatics and bioinformatics
• SNN applications in human expression and emotion recognition
• NeuCube and its applications
• SNN in neuro-robotics
• SNNs for interactions between humans and machines through vision and control
• Modelling brain EEG signals with AR/VR technology
• Any other topics related to SNN, relevant theory, and applications.


Keywords: Deep neural networks, Neuromorphic computation, Computer vision, Algorithms, Evaluations


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

Deep Neural Networks (DNNs) and their applications for computer vision have been actively developed in recent years. Along with them, methods and systems for neuromorphic computation and Spiking Neural Networks (SNNs) in particular are rapidly emerging means of neural information processing, drawing inspiration from brain processes. The prominent background of this Research Topic is that SNNs have the potential to advance technologies and techniques in fields as neuromorphic systems, deep neural networks, computer vision, image and image processing, intelligent surveillance, artificial intelligence, and indeed any fields that involve complex temporal or spatiotemporal data. SNN, as the third generation of neural networks, is able to operate on noisy data, in changing environments at low power with high effectiveness. Due to the biological foundation principles, SNN research outcomes are strongly positioned to benefit from advances made in the fields of evolutionary and cognitive neuroscience. We believe that this area is quickly establishing itself as an effective alternative to traditional machine learning, computational vision, digital imaging, and the research interest in this area is growing rapidly.

This Research Topic aims to bring together research works of contemporary areas of SNNs for computer vision, including theoretical, computational, application-oriented, experimental studies, and emerging technologies in deep neural networks, neuromorphic systems, computer vision, imaging, and video technology.

The subjects related to this Research Topic include, but are not limited to:
• New theories of spike information representation
• Learning algorithms for Deep SNNs
• Theory and analytics of SNNs
• Optimization and analysis of SNNs
• Knowledge transfer between humans and SNN machines
• Theory or practice in biologically realistic neural simulation and biometrics models
• Spike encoding methods for computer vision
• SNN model visualization and visual scene understanding
• SNN models for visual information processing
• Evolving SNN for integrated audio-visual information processing
• SNN for brain-inspired computer vision
• SNN for brain-inspired dynamic imaging
• SNN for brain-inspired video technology
• SNN for brain-inspired image processing and artifact removal
• SNN for brain-inspired time series analysis
• SNN for brain-inspired autonomous vehicles
• SNN for brain-inspired artificial intelligence
• SNN applications in neuroinformatics and bioinformatics
• SNN applications in human expression and emotion recognition
• NeuCube and its applications
• SNN in neuro-robotics
• SNNs for interactions between humans and machines through vision and control
• Modelling brain EEG signals with AR/VR technology
• Any other topics related to SNN, relevant theory, and applications.


Keywords: Deep neural networks, Neuromorphic computation, Computer vision, Algorithms, Evaluations


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

27 August 2021 Abstract
25 December 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

27 August 2021 Abstract
25 December 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..