Understanding cortical processes underlying everyday functions such as movement, speech, and cognition, and the neurological injuries and disorders that affect these functions, is a critical step for development of novel neuroprosthetic devices and clinical treatments for mitigating the effects of neurological injury. These processes can be elucidated experimentally by probing and perturbing the cortical system through use of brain-computer-interfaces (BCIs), or computationally through development of data driven cortical and artificial intelligence (AI) models. BCI technology allows for recording of brain function at multiple resolutions (single neuron, local cortical networks, and networks spanning multiple cortices) to identify spatiotemporal input-output relationships, either relating functional external parameters to cortical activity, or relating the activity between multiple cortical areas. These data driven input-output relationships can then be used to extract cortical information as command signals for a myriad of closed-loop neuroprosthetic applications. In parallel, data driven computational models of cortical activities have the potential to help us make predictions of how the brain should behave in different behavioral states (e.g. varied attention, cognition, etc.) and under different stresses, potentially leading to artificial intelligence systems that can recreate aspects of cortical function. The common thread between BCIs and AI is that both data driven approaches can lead to a more thorough understanding of brain function.
Thus, the present Research Topic aims to coalesce novel research investigations aimed at using data driven approaches in BCIs and AI for better understanding of cortical function, with the goal of developing closed-loop neuroprosthetic or clinical interventions for mitigating effects of neurological injury. Potential topics of interest are, but not limited to, 1) machine learning based approaches aimed at elucidating cortical representation and function, 2) novel signal processing methods for closed-loop decoding of cortical signals for neuroprosthetic applications, 3) identification of interactive relationships between multiple cortical areas with application to closed-loop neuromodulation systems, 3) experimental identification of cortical processes underlying behavioral functions, 4) development of data-driven computational models underlying cortical function related to movement, speech, etc…, or neurological disorders, 5) development of data driven AI models for predicting cortical behavior and/or response, and 5) develop of data driven AI models for understanding emergent behaviors of multiple cortical networks. While broad, this Research Topic requires that potential authors make clear how submitted manuscripts 1) make use of computational or experimental data driven approaches, and 2) could directly lead to clinically relevant neuroprosthetic interventions.
[Submission of Original Research work is strongly encouraged]
Understanding cortical processes underlying everyday functions such as movement, speech, and cognition, and the neurological injuries and disorders that affect these functions, is a critical step for development of novel neuroprosthetic devices and clinical treatments for mitigating the effects of neurological injury. These processes can be elucidated experimentally by probing and perturbing the cortical system through use of brain-computer-interfaces (BCIs), or computationally through development of data driven cortical and artificial intelligence (AI) models. BCI technology allows for recording of brain function at multiple resolutions (single neuron, local cortical networks, and networks spanning multiple cortices) to identify spatiotemporal input-output relationships, either relating functional external parameters to cortical activity, or relating the activity between multiple cortical areas. These data driven input-output relationships can then be used to extract cortical information as command signals for a myriad of closed-loop neuroprosthetic applications. In parallel, data driven computational models of cortical activities have the potential to help us make predictions of how the brain should behave in different behavioral states (e.g. varied attention, cognition, etc.) and under different stresses, potentially leading to artificial intelligence systems that can recreate aspects of cortical function. The common thread between BCIs and AI is that both data driven approaches can lead to a more thorough understanding of brain function.
Thus, the present Research Topic aims to coalesce novel research investigations aimed at using data driven approaches in BCIs and AI for better understanding of cortical function, with the goal of developing closed-loop neuroprosthetic or clinical interventions for mitigating effects of neurological injury. Potential topics of interest are, but not limited to, 1) machine learning based approaches aimed at elucidating cortical representation and function, 2) novel signal processing methods for closed-loop decoding of cortical signals for neuroprosthetic applications, 3) identification of interactive relationships between multiple cortical areas with application to closed-loop neuromodulation systems, 3) experimental identification of cortical processes underlying behavioral functions, 4) development of data-driven computational models underlying cortical function related to movement, speech, etc…, or neurological disorders, 5) development of data driven AI models for predicting cortical behavior and/or response, and 5) develop of data driven AI models for understanding emergent behaviors of multiple cortical networks. While broad, this Research Topic requires that potential authors make clear how submitted manuscripts 1) make use of computational or experimental data driven approaches, and 2) could directly lead to clinically relevant neuroprosthetic interventions.
[Submission of Original Research work is strongly encouraged]