🎓GeoAcademyGeoVerse Lab
← AI & Computing Sciences College

Machine Learning Department

The Machine Learning Department teaches deep learning architectures end to end - transformers for sequential geophysical data, graph neural networks for spatial relationships, physics-informed neural networks, and federated learning - from theory through implementation. Students apply these algorithms to earth-science prediction and classification tasks, experiencing the full cycle of model design, training, and evaluation. Along the way, they develop the judgment to select and tune architectures that match a dataset's character, whether temporal, spatial, or physically constrained. Graduates leave able to sit down with an unfamiliar geoscience dataset and design a fitting deep learning model from scratch, unaided.

⚙️ GeoAcademy System Administration College🖥️ AI & Computing Sciences College🔬 Basic Sciences College⚡ Intelligent Geophysical Exploration College🛢️ Resource & Energy Engineering College🌍 Applied Geoscience Solutions College💼 Economics, Policy & Strategy for the Future College🎓 Education & Training Development College🚀 Innovation & International Collaboration College
Machine Learning DepartmentComputer Vision DepartmentNatural Language Processing DepartmentHigh-Performance Computing DepartmentQuantum Computing DepartmentGenerative AI & Foundation Models CenterReinforcement Learning & Agents CenterAI Safety & Alignment CenterAI for Science CenterRobotics & Embodied AI Center

Field-based Curriculum · 15

This department's curriculum is built directly on the GeoVerse Lab research fields its professors hold — click a field to see how it is taught.

Statistical & Computational Learning Theory
Statistical & Computational Learning Theory
Through statistical learning theory, learners grasp the mathematical conditions …
Alexey Chervonenkis
Decision Trees & Ensemble Methods
Decision Trees & Ensemble Methods
Learners build decision trees on tabular geoscience data and discover, through e…
Leo Breiman
Kernel Methods & Support Vector Machines
Kernel Methods & Support Vector Machines
Learners study kernel methods and support vector machines, which achieve nonline…
James Mercer
Clustering & Unsupervised Learning
Clustering & Unsupervised Learning
Students learn how iterative clustering such as k-means discovers structure in u…
Hugo Steinhaus
Graph Theory Foundations for Graph Neural Networks
Graph Theory Foundations for Graph Neural Networks
Learners acquire the graph-theoretic vocabulary and message-passing machinery of…
Frank Harary
Federated & Privacy-Preserving Statistical Learning
Federated & Privacy-Preserving Statistical Learning
Learners study federated learning, in which participants exchange only model upd…
C. R. Rao
Self-Supervised Representation Learning & Pattern Theory
Self-Supervised Representation Learning & Pattern Theory
Learners study self-supervised learning, in which models build representations b…
Ulf Grenander
Bayesian Neural Networks & Uncertainty-Aware Deep Learning
Bayesian Neural Networks & Uncertainty-Aware Deep Learning
Students learn Bayesian deep learning, which treats network weights as probabili…
David J. C. MacKay
Stochastic Optimization & Gradient Descent Theory
Stochastic Optimization & Gradient Descent Theory
Learners study stochastic gradient descent, the optimisation engine of modern ne…
Herbert Robbins
Dimensionality Reduction & Manifold Learning
Dimensionality Reduction & Manifold Learning
Students learn multidimensional scaling and manifold learning, which compress th…
Joseph B. Kruskal
Anomaly & Novelty Detection
Anomaly & Novelty Detection
Students learn the strategy of modelling normality first and flagging departures…
Francis Ysidro Edgeworth
Meta-Learning & Learning to Learn
Meta-Learning & Learning to Learn
Learners study and implement meta-learning, which trains models across many task…
Donald Michie
Feature Selection & Information-Theoretic Variable Selection
Feature Selection & Information-Theoretic Variable Selection
Learners master information-theoretic feature selection — ranking measured varia…
Solomon Kullback
Universal Function Approximation & Neural Network Architecture Theory
Universal Function Approximation & Neural Network Architecture Theory
Learners study universal function approximation to understand what a network arc…
Vladimir Arnold
Active Learning & Sequential Experimental Design
Active Learning & Sequential Experimental Design
Students learn how active learning lets the model itself choose which data to la…
Herman Chernoff