During the last decade, the fields of neuroprosthesis and brain-computer interfaces (BCI) have rapidly grown into a phase of maturity. Numerous demonstrated prototypes have been invented, such as brain-controlled wheelchairs, keyboards, and computer games. However, current BCI systems still face critical challenges on accuracy, robustness, stability, and reliability in online control, which seriously hinders the clinical application of BCIs.
The intersection of artificial intelligence and the brain can inspire new aspects for constructing high-performance neuroprosthesis and BCIs. For example, brain-inspired neural decoding algorithm and hardware may enable more natural information transfer and computing between the brain and machine, which can potentially improve the adaption and long-term stability of BCI systems; AI-based closed-loop neurostimulation devices and therapies can improve the effectiveness and reliability of the rehabilitation and control of neurological disorders; human-in-the-loop learning strategies and neural feedback paradigms can facilitate rapid and effective BCI training.
In this Research Topic, we welcome original research articles and technical reviews that focus on the development of novel algorithms, models, systems and applications to construct high-performance BCI systems. Through this Research Topic, we are aiming to further promote the intersection of AI and neuroscience.
The scope of this Research Topic includes, but is not limited to:
- Novel brain-computer interfaces and cyborg systems that promote the close collaboration of AI and the brain, including innovative theory and models, and their theoretical, experimental and clinical applications.
- Neural decoding technologies that are based on biologically plausible computing models such as spiking neural networks, brain-inspired algorithms, and neuromorphic.
- Adaptive AI models and algorithms for closed-loop neural decoding and neural stimulation.
- Novel human-in-the-loop learning and feedback strategies for rapid BCI calibration and effective BCI training.
During the last decade, the fields of neuroprosthesis and brain-computer interfaces (BCI) have rapidly grown into a phase of maturity. Numerous demonstrated prototypes have been invented, such as brain-controlled wheelchairs, keyboards, and computer games. However, current BCI systems still face critical challenges on accuracy, robustness, stability, and reliability in online control, which seriously hinders the clinical application of BCIs.
The intersection of artificial intelligence and the brain can inspire new aspects for constructing high-performance neuroprosthesis and BCIs. For example, brain-inspired neural decoding algorithm and hardware may enable more natural information transfer and computing between the brain and machine, which can potentially improve the adaption and long-term stability of BCI systems; AI-based closed-loop neurostimulation devices and therapies can improve the effectiveness and reliability of the rehabilitation and control of neurological disorders; human-in-the-loop learning strategies and neural feedback paradigms can facilitate rapid and effective BCI training.
In this Research Topic, we welcome original research articles and technical reviews that focus on the development of novel algorithms, models, systems and applications to construct high-performance BCI systems. Through this Research Topic, we are aiming to further promote the intersection of AI and neuroscience.
The scope of this Research Topic includes, but is not limited to:
- Novel brain-computer interfaces and cyborg systems that promote the close collaboration of AI and the brain, including innovative theory and models, and their theoretical, experimental and clinical applications.
- Neural decoding technologies that are based on biologically plausible computing models such as spiking neural networks, brain-inspired algorithms, and neuromorphic.
- Adaptive AI models and algorithms for closed-loop neural decoding and neural stimulation.
- Novel human-in-the-loop learning and feedback strategies for rapid BCI calibration and effective BCI training.
