Recipients of the Uplimit Interpreting Machine Learning Models certificate have gained knowledge of a range of techniques for explaining predictions made by classifiers that have been trained on language, vision, and tabular data. The comprehensive course has been designed to provide a practical understanding of various algorithms for interpretability, allowing the recipients to benchmark commonly used ML models for their faithfulness and plausibility. Furthermore, the course covers the fundamentals of how certain explanations can aid in the identification of artifacts and assist in the creation of more reliable ML models.

Certification criteria:

Actively participated in Uplimit's dynamic course on Interpreting Machine Learning Models: attended lectures, project sessions, fireside chats with industry leaders, and more.

Learned the fundamentals of interpreting machine learning models, specifically deep learning models that are pre-trained on large amounts of data using self-supervision

September 13, 2023 Instructor: Nazneen Rajani

issued by

Developed best practices for interpreting image classification models, text classification models, evaluating explanations, and how to robustify ML models.