Get the latest tech news

How important is explainability? Applying clinical trial principles to AI safety testing


Explainability is a heightened focus in AI. How existing scientific techniques can ensure AI is working as intended — and safely.

Similarly, Google Deepmind’s cancer screening models use deep learning methods to build accurate disease detection that can save lives. This framework allowed technology companies like Bing — and later Uber, Airbnb and many others — to make iterative changes to their products and user experience and understand the benefit of these changes on key business metrics. The result is that many companies now have a system to iteratively test changes to a technology against a control or a benchmark: One that can be adapted to measure not just business benefits like clickthrough, sales and revenue, but also causally identify harms like disparate impact and discrimination.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of explainability

explainability

Photo of AI safety testing

AI safety testing

Related news:

News photo

How important is explainability? Applying clinical trial principles to AI safety testing