Giridhar Sunil is a MaSc candidate in the Electrical and Computer Engineering Department at Concordia University. His current research is focused on analysising the patterns in the synaptic and extrasynaptic connections of C. Elegans. He has expertise in Machine Learning and Deep learning, Software engineering, Data analysis and Computer Vision.
He received his B.Tech degree in Computer Science Engineering from Vellore Institute of Technology.
Understanding the foundational principles of neural communication remains a grand challenge in neuroscience, particularly when it comes to disentangling the multiplexed signaling strategies employed by biological systems. Caenorhabditis elegans, a model organism with a fully mapped synaptic connectome, also exhibits a parallel mode of information transmission through extrasynaptic signaling—facilitated by neuropeptides and monoamines—that is not constrained by direct anatomical connections. Despite its simplicity in neuronal count, the worm leverages this dual signaling architecture to coordinate a broad repertoire of behaviors. In this work, we aim to explore the functional interplay between the synaptic (wired) and extrasynaptic (wireless) connectomes. In the first phase, we segment the extrasynaptic connectome using Kubo-Martin-Schwinger (KMS) states to classify and analyze the dependence of extrasynaptic circuits on synaptic topology. In the second phase, we employ topological data analysis—specifically persistent homology and clustering techniques—to extract higher-order structures and functional motifs embedded within these neural networks. By integrating graph-theoretic and topological tools, our objective is to elucidate how C. elegans exploits extrasynaptic communication to compensate for anatomical limitations, providing insights into the design principles of robust, adaptable neural systems.
Giridhar, S., Sreeram, K.P., Menon, N., Ravikumar, A. and Sriraman, H., 2024. An Intelligent System for Preventing Accidents Due to Driver Distractions. Procedia Computer Science, 235, pp.2196-2204.
Sunil, G. and Kuriakose, A., 2023. Emotion Detection with CNN Model and Song Recommendations using Machine Learning Techniques. Emotion, 3(3).
Alla, S., Giridhar, S., Kunjumon, C.T., Sriraman, H. and Chattu, V.K., 2024. Hiatal Hernia Detection Using Novel End-to-End Deep Learning Model with Explainable AI. In IISE Annual Conference. Proceedings (pp. 1-6). Institute of Industrial and Systems Engineers (IISE).
