[safe-ai]

Projects

Ethical and Explainable AI in Fintech applications

Machine Learning and AI have become inevitable workhorses behind algorithms in data- centric domains such as Fintech. While dealing with sensitive data in such domains, it becomes essential to make sure that the data is used in an ethical and fair manner, and predictions made by learning algorithms are explainable.

Read More

Explainable GI Endoscopy Procedure Assessments

Gastrointestinal (GI) Endoscopy is a medical procedure wherein a trained medical expert (henceforth referred to as endoscopist) uses a flexible endoscope to examine the GI tract to screen for various diseases.

Read More

Human-in-the-loop for Safe and Verifiable Reinforcement Learning

One of the main challenges in implementation of RL in real life applications is safety. Particularly, the undesired and harmful behaviour of RL agents involving humans is one of the major safety concerns.

Read More