Special Issue on Spiking Neural Networks for Deep Learning and Knowledge Representation: Theory, Methods, and Applications
• 大类 : 工程技术 - 1区
• 小类 : 计算机：人工智能 - 2区
• 小类 : 神经科学 - 2区
Spiking Neural Networks (SNN) are a rapidly emerging means of information processing, drawing inspiration from brain processes. SNN can handle complex temporal or spatiotemporal data, in changing environments at low power and with high effectiveness and noise tolerance. Today’s success in deep learning is at the cost of brute-force computation of large bit numbers by power-hungry GPUs. Due to their basis in biological neural networks, SNN research is strongly positioned to benefit from advances made in the fields of molecular, evolutionary and cognitive neuroscience. This area is quickly establishing itself as an effective alternative to traditional machine learning technologies, and the interest in this area of research is growing rapidly.
This special issue on SNN invites researchers to present state-of-the-art approaches, recent advances and the potential of SNN. Topics include theoretical, computational, and application-oriented studies of SNN, as well as emerging technologies such as neuromorphic hardware. More specifically we are looking for methods for deep learning of temporal, spatio-temporal and streaming data with SNN, along with methods for the analysis of trained SNN to represent new knowledge and understanding of the data and processes that are measured.
Main Topics include:
The topics relevant to this special issue include, but are not limited to, the following:
- Learning algorithms for SNN, including Deep Learning
- Theory of SNN
- New information theories based on spike information representation
- Big data and stream data processing in SNN
- SNN model visualisation for the sake of model and data understanding
- Neuromorphic hardware systems and applications
- Optimization of SNN
- SNN models of cognitive development
- SNN for brain-inspired artificial intelligence
- Knowledge transfer between humans and spiking neural network machines
- SNN applications in neuroinformatics, bioinformatics, medicine and ecology.