Bye-bye, Miss AI

The presentation describes a need to implement explainable AI.

Transcript

1. Kacper Łukawski, Data Science Lead at Codete
2. Agenda: AI hype ML project lifetime Real-life story XAI
3. Forty percent of “AI startups” in Europe don’t actually use AI The State of AI 2019: Divergence AI hype
4. Startups labelled as being in AI attract 15% to 50% more funding than other technology firms. The State of AI 2019: Divergence AI hype
5. 1. Data wrangling 2. Model training 3. Validation 4. Inference ML project lifetime
6. ML project lifetime 1. Data wrangling 2. Model training 3. Validation 4. Inference
7. Real-life story
8. 1. Sweet little girl 2. Her grandmother 3. Little red cap 4. A piece of cake and a bottle of wine to be delivered 5. Big bad wolf Real-life story
9. The question is: How to distinguish grandma from a wolf? Real-life story
10. It doesn’t matter what is the issue. Our Little Red Riding Hood needs some support so badly. The original story comes from the 17th century and at this time there was no rescue, but now we have AI! Real-life story
11. There is a well-known example of a Machine Learning system designed for classifying the images of wolves and huskies. Classification: wolf or a husky?
12. Even though, just by looking at the numbers, everything may seem to work perfectly, we need to understand how it works behind the scene. Classification: wolf or a husky?
13. We are in a point, when we desperately need AI that can be explained. In other words, our models cannot just make the decisions - they need to clarify them as well or at least allow to be clarified. XAI
14. Thank you! Kacper Łukawski kacper.lukawski@codete.com