Memories on the time scale of seconds to tens of seconds are stored as patterns of neural activity that persist long after the offset of a stimulus. This persistent neural activity is believed to be critical for processing new information and forming cognitive perceptions. Recent studies suggest that purely circuit-based mechanisms are insufficient to explain the robustness of persistent activity to biological noise and perturbation. This proposal will test the hypothesis that persistent activity is maintained by a hybrid cellular/circuit mechanism in which circuit level feedback mediates the activation of memory processes in a neuron's dendrites known as plateau potentials. To quantitatively understand how active dendritic properties contribute to persistent activity, a new modeling framework will be developed to directly and simultaneously fit a memory network to data from a diverse set of experiments characterizing intrinsic excitability, anatomical connectivity, neural coding, and response to perturbations. These models will be used to predict the patterns of dendritic activity that can be seen with fluorescence calcium imaging. To test these predictions, the zebrafish preparation will be used to directly measure dendritic activity during eye movement behavior from cells storing a memory of desired eye position. Two-photon imaging of calcium indicators will be used to measure spatiotemporal patterns of activity in the dendritic neuropil, and separately in individual dendritic branchlets, to determine the presence of plateau potentials. Together, these computational and experimental results will help determine how cellular and circuit properties work in concert to generate one of the most important brain dynamics, persistent neural activity.
