Gaurav Singh

Research profile

Applied machine-learning researcher working across visual-mathematical literacy, computer vision, generative modelling, and nonlinear simulation. My background combines computer science, design, and a decade of university teaching. I also maintain Mathscapes as an independent mathematical practice.

Research interests

Applied machine learning, mathematical modelling, computer vision, time-series and generative models, statistical inference, human-computer interaction, and algorithmic literacy.

Education

Publications

A Framework for Visual-Mathematical Literacy in Applied Machine Learning: Why Representation Choices Shape What Models Can Learn. G. Singh, R. S. Dhari. Machine Learning: Engineering, 2026. doi:https://doi.org/10.1088/3049-4761/ae7df3
Techno-Economic Pathways Modeling and Nonlinear Optimized SEEA-ROI Longitudinal Dynamic Simulation for Decarbonizing Australian Heavy Transportation Systems. G. Singh, E. Chang, Y. Karaca. Fractals, 2026. doi:https://doi.org/10.1142/S0218348X26400633
Automated detection of deformation mechanisms in re-entrant honeycomb auxetics using machine learning. G. Singh, R. S. Dhari, Z. Javanbakht. International Journal of Protective Structures, 2025. doi:https://doi.org/10.1177/20414196241281069
ReRide: A Bike Area Network for Embodied Self-monitoring during Motorbike Commute. N. Bagalkot, G. Singh, V. Rath, T. Sokoler, A. Shukla. TEI 2019, 443-450, 2019. doi:https://doi.org/10.1145/3294109.3300986
ReRide. N. Bagalkot, T. Sokoler, R. Shaikh, G. Singh, A. E. Lillie, P. Dixit, A. Rai, V. Chakravarthy, A. Senthil. INTERACT 2017, LNCS 10516, 2017. doi:https://doi.org/10.1007/978-3-319-68059-0_43
SnapTag: Leveraging Situated Memory to enhance self-efficacy for well-being. S. Baadkar, G. Singh, A. Saraf, N. Bagalkot. India HCI 2014, 136-141, 2014. doi:https://doi.org/10.1145/2676702.2676719

Academic experience

Teaching and academic leadership

Designed and taught 30 courses and workshops over a decade (2013–2022), mostly at Srishti Manipal Institute in Bangalore, spanning creative coding, algorithmic botany, physical computing, machine learning, interaction design, and human-computer interaction.

Technical methods

Python, scikit-learn, computer vision, time-series and generative modelling, statistical inference, nonlinear optimisation, experimental design, and data visualisation.

Awards

Academic service and supervision

References available on request.