ECLIPSE Lab — Presentations & Teaching

Lecture slides, conference talks, and course materials from the ECLIPSE Lab at FAU Erlangen-Nürnberg.

Data Science for Electron Microscopy

Week 01
Python crash course & course launch
Open Slides Source
Week 02
What is learning? EM data & where noise comes from
Open Slides Source
Week 03
Linear algebra & PCA you actually need
Open Slides Source
Week 04
Regression, gradient descent & honest validation
Open Slides Source
Week 05
Neural networks from first principles
Open Slides Source
Week 06
CNNs for microscopy images
Open Slides Source
Week 07
Beating small & expensive data
Open Slides Source
Week 08
Unsupervised learning & autoencoders for EM
Open Slides Source
Week 09
Probability, uncertainty & Gaussian processes
Open Slides Source
Week 10
Active & automated electron microscopy
Open Slides Source
Week 11
Imaging inverse problems I
Open Slides Source
Week 12
Imaging inverse problems II — ptychography, physics-informed & generative
Open Slides Source
Week 13
Explainability, trust & course synthesis
Open Slides Source

Mathematical Foundations of AI & ML

Unit 01
Learning vs Data Analysis; Models, Loss Functions
Open Slides Source
Unit 02
Linear Algebra Refresher; Covariance, PCA/SVD
Open Slides Source
Unit 03
Regression as Loss Minimization
Open Slides Source
Unit 04
Neural Networks — From Neurons to CNNs
Open Slides Source
Unit 05
Clustering & Autoencoders
Open Slides Source
Unit 06
Loss Landscapes & Optimization Behavior
Open Slides Source
Unit 07
Probabilistic View of Learning; Noise; Conformal Prediction
Open Slides Source
Unit 08
Tree Ensembles for Tabular Learning
Open Slides Source
Unit 09
Latent Spaces & Advanced Representation Learning
Open Slides Source
Unit 10
Attention & Transformers
Open Slides Source
Unit 11
Generative Models — VAE & Diffusion
Open Slides Source
Unit 12
Uncertainty in Predictions
Open Slides Source
Unit 13
Physics-Informed & Constrained Learning
Open Slides Source
Unit 14
Explainability, Limits, and Scientific Trust
Open Slides Source

Materials Genomics

Unit 01
What is Materials Genomics?
Open Slides Source
Unit 02
QM Postulates, Solvable Systems, Multi-Electron Atoms
Open Slides Source
Unit 03
Quantum Chemistry Methods (HF, MP, CC, DFT)
Open Slides Source
Unit 04
Thermodynamics, Statistical Mechanics & Classical Atomistic Simulation
Open Slides Source
Unit 05
Monte Carlo Sampling & Continuum Mechanics
Open Slides Source
Unit 06
Local Atomic Environments & Universal MLIPs
Open Slides Source
Unit 07
Graph-Based Crystal Representations
Open Slides Source
Unit 08
Regression and Generalization in Materials Data
Open Slides Source
Unit 09
Neural Networks for Materials Properties
Open Slides Source
Unit 10
Representation Learning and Feature Discovery
Open Slides Source
Unit 12
Generative Models & Inverse Design
Open Slides Source
Unit 13
Uncertainty-Aware Discovery & Gaussian Processes
Open Slides Source
Unit 14
Physical Constraints, Trust, and Integration Outlook
Open Slides Source

Machine Learning for Characterization and Processing

Unit 01
What makes materials data special?
Open Slides Source
Unit 02
Physics of data formation
Open Slides Source
Unit 03
Data quality, labels, and leakage
Open Slides Source
Unit 04
From classical microstructure metrics to learned representations
Open Slides Source
Unit 05
Unsupervised methods for materials — clustering & autoencoders
Open Slides Source
Unit 06
Data scarcity & transfer learning
Open Slides Source
Unit 07
Time-series and process monitoring (W7 self-study lecture)
Open Slides Source
Unit 08
Inverse problems and process maps
Open Slides Source
Unit 09
ML for characterization signals
Open Slides Source
Unit 10
Transformers for materials characterization (ViT, Flash Attention, Mamba)
Open Slides Source
Unit 11
Uncertainty-aware regression & Gaussian Processes
Open Slides Source
Unit 12
Physics-informed and constrained ML
Open Slides Source
Unit 13
Integration, limits, and reflection
Open Slides Source

Conference Talks

Talk
2025 MC
Open Slides Source
Talk
2025 M&M
Open Slides Source

← Back to ECLIPSE Lab