C201: AI for Scientific Discovery

Duration: 12 hours

This module introduces the core ideas behind artificial intelligence and machine learning. Learners will build the mathematical and computational foundation needed to understand how AI methods are used in scientific contexts.

Topics include AI vs machine learning vs deep learning, the scientific value of AI, linear algebra, probability, Bayes’ theorem, optimization, and basic Python tools such as NumPy, Matplotlib, and Jupyter notebooks.

By the end of this module, learners will be able to understand the basic workflow of scientific machine learning and run simple exploratory experiments with data.

Duration: 12 hours

This module focuses on the use of AI in physical science problems. Learners will study supervised and unsupervised learning methods, data fitting, classification, neural networks, dimensionality reduction, and modern AI techniques used in physics research.

Applications include experimental data fitting, parameter estimation, phase classification, particle physics, astrophysics, cosmology, quantum systems, gravitational-wave detection, physics-informed neural networks, and symbolic regression.

This module is designed to help learners connect machine learning techniques with scientific interpretation and physical reasoning.

Duration: 12 hours

This module explores how AI is transforming chemical research and analysis. Learners will study chemical data types, data representation methods, public chemical databases, and machine learning approaches used in chemistry.

Topics include molecular descriptors, fingerprints, SMILES, InChI, PubChem, ChemSpider, ChEMBL, Protein Data Bank, spectroscopic data, reaction data, and prediction tasks in chemistry.

Applications include medicinal chemistry, materials chemistry, electrochemistry, green chemistry, synthesis planning, reaction optimization, and AI-assisted interpretation of chemical data.