One of my post-docs, and I was previously on the supervisory team for her PhD, has been partly occupying her time generating publications from her thesis. This is one such. She's addressing the question of what people actually want when they ask that an autonomous system provide explanations. In particular, though she doesn't really get into that in the paper, most explainability research has focused specifically on neural networks that are classifying things into groups, not on robotic systems that are taking decisions about what to do next.

Eliciting Explainability Requirements for Safety-Critical Systems: A Nuclear Case Study talks through her approach, and tries to categorise her results into groups. There is also some formalisation of the requirements into logic, though via the use of structured English to make it more comprehensible. Lastly she reports on some lessons learned.

Two Doctor Who companion outfits for your delectation and delight! Outfits selected by a mixture of ones I, personally, like; lists on the internet; and a certain random element.


( Outfits below the Cut )

Vote for your favourite of these costumes. Use whatever criteria you please - most practical, most outrageously spacey, most of its decade!

Voting will remain open for at least a week, possibly longer!

Costume Bracket Masterlist

Images are a mixture of my own screencaps, screencaps from Lost in Time Graphics, PCJ's Whoniverse Gallery, and random Google searches.

The award winning paper I mentioned next week, actually had a sequel. In The human factor: Addressing computing risks for critical national infrastructure towards 2040 we performed a similar exercise of asking a number of experts about risks to Critical National Infrastructure arising from computing developments and synthesising the results.

I am honestly, happier with this paper, I thought we had a better range of genuine expertise in the people we talked to, and a more focused area of consideration. We had a little trouble with the third referee, who thought our experts were wrong about Quantum Computing and that we should rewrite the paper so they gave the answer the referee thought was correct. Our experts did not think Quantum Computing was among the biggest risks to be considered in the next 15 years - but instead thought there were a number of issues relating to human factors (sophisticated phishing, difficulty tracing the cause of problems and poor incident response in complex situations).

Two Doctor Who companion outfits for your delectation and delight! Outfits selected by a mixture of ones I, personally, like; lists on the internet; and a certain random element.


( Outfits below the Cut )

Vote for your favourite of these costumes. Use whatever criteria you please - most practical, most outrageously spacey, most of its decade!

Voting will remain open for at least a week, possibly longer!

Costume Bracket Masterlist

Images are a mixture of my own screencaps, screencaps from Lost in Time Graphics, PCJ's Whoniverse Gallery, and random Google searches.