Title:  Signal analysis and modeling in neuroscience

Session Chairs: Jing Wang (University of Missouri) and Ilker Ozden (University of Missouri)



Methods for analyzing neural signals, large scale neural data, neural dynamics, functional imaging, neural circuitry, fMRI, EEG, electrophysiology, population spiking, Machine learning, deep learning, neural networks, computation models of the brain, connectomics, disease models and neuropathologies



Signals in the brain are highly complex and dynamical. Technologies (such as neuronal population recording, EEG and functional imaging), targeting brain dynamics at different spatial-temporal levels have provided complementary information about brain function. Advances in analyzing those large scale and dynamical data of the neural system were heavily indebted to the low cost of computation and data sharing recently. Artificial Intelligence (AI) also makes it possible to develop solutions to detect, monitor, prevent, and treat neurological diseases. More importantly, neuroscience research has been reshaping its course by the new wave of AI development. Methods of deep learning, particularly building neural networks grounded in quasi-realistic signals of the brain, have helped neuroscientists better understand the underlying processes in the brain and test hypotheses at various levels. In parallel, findings in neuroscience constantly inspire new AI algorithms (reinforcement learning, attention and memory), whose applications extend beyond biological systems. This workshop provides a platform for conversations with hopes of intellectual synergy between AI and neuroscience research.

In addition to papers on regular AIPR topics in applied imagery. This special session invites papers that address aspects of developments in AI and neuroscience, including but not limited to the tools for analyzing neural signals (behavioral, population neuronal spiking, cellular imaging, EEG, fMRI and etc.), methodologies, algorithms, models and mechanisms of the brain functions.