Conventional computing systems have been facing challenges in terms of energy efficiency and massive data processing when handling big data in various applications. The challenges mainly come from the von Neumann architecture-based processor used in the systems where memory and the central processing unit are separated, causing the von Neumann bottleneck.
Neuromorphic computing system is one of the novel and promising candidates to overcome the limitations of the conventional computing systems by adopting and mimicking the human brain neural network and its parallel processing method. The field of research in the neuromorphic engineering spans a wide range of research fields and layers from materials and devices to system and algorithm. However, in order to develop and realize an energy efficient neuromorphic computing system, it is necessary to integrate each research field and layer and build as a whole system. Although there are already many themes in different layers of research, the importance of integration studies between the layers, e.g., circuits based on emerging synaptic device array, for building neuromorphic system has not yet been intensively considered. This Research Topic will focus on the latest advances in neuromorphic engineering for integrated research between the layers as well as each subject-specific research field.
Topics of interest include (but are not limited to) the following:
- Implementation of brain-inspired time-, event-, or data-driven computing systems through the novel integration of materials, devices, systems, and neuromorphic algorithms
- Analog/digital circuits for neuromorphic systems
- Spiking neural networks (SNN)
- Time-, event-, or data-driven learning algorithms to facilitate neuromorphic system implementation
Conventional computing systems have been facing challenges in terms of energy efficiency and massive data processing when handling big data in various applications. The challenges mainly come from the von Neumann architecture-based processor used in the systems where memory and the central processing unit are separated, causing the von Neumann bottleneck.
Neuromorphic computing system is one of the novel and promising candidates to overcome the limitations of the conventional computing systems by adopting and mimicking the human brain neural network and its parallel processing method. The field of research in the neuromorphic engineering spans a wide range of research fields and layers from materials and devices to system and algorithm. However, in order to develop and realize an energy efficient neuromorphic computing system, it is necessary to integrate each research field and layer and build as a whole system. Although there are already many themes in different layers of research, the importance of integration studies between the layers, e.g., circuits based on emerging synaptic device array, for building neuromorphic system has not yet been intensively considered. This Research Topic will focus on the latest advances in neuromorphic engineering for integrated research between the layers as well as each subject-specific research field.
Topics of interest include (but are not limited to) the following:
- Implementation of brain-inspired time-, event-, or data-driven computing systems through the novel integration of materials, devices, systems, and neuromorphic algorithms
- Analog/digital circuits for neuromorphic systems
- Spiking neural networks (SNN)
- Time-, event-, or data-driven learning algorithms to facilitate neuromorphic system implementation