Calibration and Generalizability of Probabilistic Models on Low-Data Chemical Datasets
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore a comprehensive conference talk on calibration and generalizability of probabilistic models for low-data chemical datasets. Delve into the DIONYSUS study, which examines various molecular representations and models for predicting molecular properties. Learn about three key experiments: performance analysis, Bayesian optimization for molecular design, and out-of-distribution inference using ablated cluster splits. Gain practical insights into model and feature selection for small chemical datasets, a common scenario in new chemical experiments. Discover the open-source DIONYSUS repository, designed to aid reproducibility and extension to new datasets. Follow along with the speaker's in-depth analysis, covering motivations, experimental overviews, and practical recommendations, concluding with a Q&A session.
Syllabus
- Intro
- Motivations
- Overview of Proposed Experiments
- Experiment 1: Study of Performance
- Experiment 2: Bayesian Optimization
- Experiment 3: Generalization and Ablation
- Practical Insights & Recommendations
- Q+A
Taught by
Valence Labs
Related Courses
Fundamentals of Quantitative ModelingUniversity of Pennsylvania via Coursera Теория вероятностей – наука о случайности
Tomsk State University via Stepik Statistics and Data Science
Massachusetts Institute of Technology via edX Natural Language Processing with Probabilistic Models
DeepLearning.AI via Coursera Natural Language Processing
DeepLearning.AI via Coursera