Reimagining Chemistry Pedagogy through Modeling, Computation & AI-driven Discovery

Models now predict the properties of a molecule before it is made, propose new compounds, choose reaction conditions, and drive automated experiments. Behind every one of these systems is a small amount of linear algebra, applied well. This one-day workshop, delivered by the Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, is built for students who have not studied machine learning before.

The morning builds the mathematics from first principles: vectors, matrices, the pseudoinverse, regression, classification, and how a neural network can be trained without backpropagation. The afternoon is hands-on — you write Python that turns molecules into numbers, fit a property model to a real dataset, and hand the same tools to an AI agent that carries out a computational-chemistry task from a plain-English request.