We are seeing an overwhelming growth in AI/ML systems to process oceans of Data that is being generated in the new digital economy. However, with this growth, there is a need to seriously consider the ethical and legal implications of AI.
This talk will introduce you to the concept of Responsible AI and how it can help you build better systems. We will cover several facets of Responsible AI like Standardization, Reproducibility, Transparency, Security, and Privacy. You will see samples of a standardized ML pipeline covering several aspects of the ML model development lifecycle. We will also show you how explainable AI can be incorporated into this cycle to give a true picture of what your model is learning and conduct fairness reviews.
Finally, we will cover the topics of Security and Privacy and discuss enabling technologies for the same as federated learning, secure aggregation, and homomorphic encryption.