Leadership Instincts: UW launches Faculty Diversity Initiative  |  Parent Interventions: Participating in engagement schemes improves young people’s wellbeing  |  Teacher Insights: Foreign language learners should be exposed to slang in the classroom   |  Teacher Insights: Site announced for new specialist mathematics school   |  Parent Interventions: New research shows north-south divide in family law  |  Teacher Insights: Lancaster Castle provides focus for lecture on importance of heritage sites  |  Teacher Insights: Tactile books adapted for blind children  |  Parent Interventions: 'Sleep hygiene' should be integrated into epilepsy diagnosis & management   |  International Edu News: University of Birmingham signs up to global UN agreement   |  International Edu News: Credit card-sized soft pumps power wearable artificial muscles  |  Parent Interventions: High fructose diets could cause immune system damage  |  International Edu News: Submit short films to Bristol Science Film Festival 2021  |  International Edu News: Attachable Skin Monitors that Wick the Sweat Away​  |  Parent Interventions: Scientists model a peculiar type of breast cancer  |  International Edu News: NTU Singapore student start-up builds robots for pandemic-proof delivery  |  
February 09, 2021 Tuesday 11:45:59 AM IST

Intersection of algebra & geometry for better machine learning algorithms

Teacher Insights

Scientists may soon develop robust algorithms that can provide more efficient machine-learning applications by focusing on concepts that lie at the intersection of algebra and geometry. Hariharan Narayanan, Assistant Professor, Tata Institute of Fundamental Research Mumbai, a recipient of this year’s SwarnaJayanti fellowship instituted by the Department of Science & Technology, Govt. of India, wishes to create machine-learning algorithms that can learn from observations and make improved predictions based on mathematical objects known as manifolds and Lie groups. This can lead to improved modelling of data arising from certain sources, such as visual observations.

Machine learning can be broadly defined as a discipline whose goal is to enable a computer to make inferences from observed data about future observations. There are two directions in which progress is crucial to make progress in machine learning. The first is making inferences from very few observations. The second is dealing with complex data, which has come to prominence through recent applications in vision, imaging like Cryo-electron Microcrope and the World Wide Web. The use of manifolds and Lie groups can help to address both of these issues and may lead to algorithms that make better predictions in real-life applications.

Comments