Interpretability of AI Solutions: Strategic Overview

Explainable AI and interpret-ability of AI solutions: Strategic overview challenges and caveats

Presented By Kriti Doneria
Kriti Doneria
Kriti Doneria
Decision Scientist at ZS||Analyst at Absolutdata

Currently, Kriti works closely to design data-driven business decisions support systems for Fortune 500 companies. Her research interests revolve around emerging technologies and algorithms (Cloud computing, AI/Ml, AR/VR, etc).In the past, she has also been one of the highest rated competitive coders in the country.

Kriti holds an MBA (Analytics and marketing) from IIT Kanpur and B.Tech in computer science.

Presentation Description

With the exponential increase in computing power available, several AI algorithms that were mere papers written decades ago have become implementable. For a data scientist, it is very tempting to use the most sophisticated algorithm available. But given that its applicability has moved beyond academia and out into the business world, are numbers alone sufficient? Putting context to AI, or XAI (explainable AI) takes the black box out of AI to enhance human-computer interaction. This talk shall revolve around the interpret-ability-complexity trade-off, challenges, drivers and caveats of the XAI paradigm, and an intuitive demo of translating inner workings of an ML algorithm into human understandable formats to achieve more business buy-ins.

Presentation Curriculum

Explainable AI and interpret-ability of AI solutions: Strategic overview challenges and caveats
43:33
Hide Content