Materials Informatics by Taylor Sparks https://www.youtube.com/playlist?list=PLL0SWcFqypCl4lrzk1dMWwTUrzQZFt7y0

PROGRAM OUTLINE NOTE: All times Eastern Daylight Time (UTC-4:00). A few introductory lecture videos will be posted ahead of the course.

Day One

9am-noon: Foundations in material informatics (data science and basic concepts of machine learning; multiscale modeling; datasets, experimental methods for data collection)

1-2pm: Clinic #1: Convolutional neural network (classifier, regression, and peeking inside via interpretable methods)

2-4pm: Digging deeper: Deep neural nets, loss functions, Stochastic optimization methods (e.g., stochastic gradient descent and variants), Regularization

4-5pm: Clinic #2: Material failure analysis

5-7pm: Interactive virtual networking reception (get to know peers, the instructor, and make connections)

Day Two

9-10am: Hands-on introduction to PyTorch (example application to fine-tuning a BERT NLP model applied to proteins)

10-11am: Hands-on introduction to TensorFlow (example application to developing an adversarial neural network)

11am-noon: Practical guide to tensor algebra and other important math concepts needed

1-2pm: Ethics, bias and sustainability in material informatics

2-3:30pm: Data, data, everywhere…De novo dataset construction (imaging lab) and application to build a deep neural network (covers computer vision tools, live imaging using depth camera

3:30-5pm: Introduction to graph neural networks (applications to molecular systems, truss systems, alloys, proteins, and healthcare; graph transformers)

Day Three

9-10:30am: Transforming AI and healthcare with attention (AlphaFold and applications to protein design, synthesis)

10:30am-noon: Deepening the understanding of language models applied to materials (pre-training and fine-tuning); BERT and GPT-3-like (applications of large language models to materials problems; category theory; time-dependent material phenomena)

1-2pm: Clinic #3: Transformer models for inverse materials design (develop multiscale transformer model from scratch)

2-3pm: Adversarial neural networks and applications to materials design (manufacturing, inverse problem, characterization)

4-5pm: Case study: Image segmentation in microscopy, medical imaging, and analysis

Day Four

9-10am: Autoencoders (vision, graphs, NLP, proteins)

10-11am: Clinic #4: To fail or not to fail: Buckling modeling (time-dependent phenomena)

11am-noon: Concluding discussion

Noon-12:30pm: Graduation ceremony and certificates