University Guest Lectures
by IBM Academic Ambassadors
Found 3 results
In the world we live in today, we are faced with a myriad of complex problems that are best solved with a blended approach of traditional and non-traditional problem solving methods.
Design Thinking offers that sought after blended approach to innovative …
A tale of adversarial attacks & out-of-distribution detection stories
Most deep learning models assume ideal conditions and rely on the assumption that test/production data comes from the in-distribution samples from the training data. However, this assumption is not satisfied in most real-world applications. Test data could differ from the …
Fairness, Explainability & Robustness in Machine Learning
Recent years have seen an overwhelming body of work on fairness and bias in Machine Learning (ML) models. This is not unexpected, as fairness is a complex and multi-faceted concept that depends on context and culture. Particularly in machine learning, …