Chennai, March 25 – Professor Shyamala Sivakumar recalls how, as a child, her mother always encouraged her to learn to draw 'pulli' kolams. The tradition of creating intricate patterns by looping lines over dots, particularly the 'sikku' or one-stroke kolam, was a common practice in southern India.
Shyamala, who teaches Computing Information Systems at Saint Mary's University in Canada, says she has never been able to master this art, despite her best efforts. Decades later, Shyamala did manage to create kolams. However, she didn't use traditional rice flour. Instead, she focused on creating formulas that could enable AI to create even more complex patterns than humans can.
This research, developed in collaboration with her husband Seshadri Sivakumar, Founder and Chief Consultant at Florida-based Pasumai EnergyTech, transforms a traditional morning ritual into a complex computational challenge.
Their research on an algorithm for generating one-stroke kolams has recently been published in Nature’s Heritage Science, an international journal that publishes peer-reviewed research.
The couple, who emigrated to Halifax, Canada, in the 1980s, say they stumbled upon this algorithm while studying 2D art and generative learning using recurrent neural networks (RNN).
Sivakumar, originally from Vellore, who worked for four years at Bharat Heavy Electrical Ltd (BHEL) before moving to Canada, says they realized that drawing lines around a grid of dots was essentially a sophisticated topological puzzle.
"Kolam patterns also possess a complex mathematical structure that has attracted significant research interest, spanning fields from computational geometry and graph theory to sociology and human-computer interaction," Sivakumar told