2021/06/09 by Dawna Bagherian, James Gornet, Jeremy Bernstein +3 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · #Advanced Fluorescence Microscopy Techniques #Biological neural network #Cell Image Analysis Techniques #Constraint (computer-aided design) #Domain (mathematical analysis) #Electronic circuit #Identifiability #Identification (biology) #Neural dynamics and brain function #Nonlinear system #Nonlinear system identification #System identification #cs.LG #q-bio.QM
paper · pdf · doi:10.1145/3447548.3467402
Preprint. 11 pages, 8 figures. Accepted Research Track paper to appear at KDD '21, August 14-18, Virtual Event, Singapore
arxiv created 2021/06/09 · arxiv updated 2021/06/11 · openalex created_date 2021/06/22 · openalex publication_date 2021/08/12 · openalex updated_date 2026/08/05
We study the problem of sparse nonlinear model recovery of high dimensional compositional functions. Our study is motivated by emerging opportunities in neuroscience to recover fine-grained models of biological neural circuits using collected measurement data. Guided by available domain knowledge in neuroscience, we explore conditions under which one can recover the underlying biological circuit that generated the training data. Our results suggest insights of both theoretical and practical interests. Most notably, we find that a sign constraint on the weights is a necessary condition for system recovery, which we establish both theoretically with an identifiability guarantee and empirically on simulated biological circuits. We conclude with a case study on retinal ganglion cell circuits using data collected from mouse retina, showcasing the practical potential of this approach.