Chennai, March 25 – Professor Shyamala Sivakumar recalled how, as a child, her mother always encouraged her to draw "pulli" kolams. The tradition of creating intricate patterns by looping a line over dots, particularly the "sikku" or single-stroke kolam, was something that most young girls in southern India were expected to learn.
Shyamala, who teaches Computing Information Systems at Saint Mary's University in Canada, said she had never been able to master this art despite her best efforts. Decades later, Shyamala did manage to create a kolam. However, she didn't use traditional rice flour; instead, she developed formulas that could enable AI to create far more complex patterns than humans can comprehend.
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 computationally challenging task.
Their research on an algorithm for single-stroke kolam generation 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, stumbled upon the algorithm while studying 2D art and generative learning using recurrent neural networks (RNN).
Sivakumar, originally from Vellore, pursued Electrical Technology and Electronics at the Indian Institute of Science in Bengaluru and worked for four years at Bharat Heavy Electrical Ltd (BHEL) before moving to Canada. He explained that the ancient practice of 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