The other idea — "algorithmic explainability" — would require companies to explain to consumers how their algorithms make decisions.
One is a definition: What do we mean by explainability?
Currently there is a trade-off in some tasks between performance and explainability, in addition to business ramifications.
The resulting feature recognition system shows a high level of flexibility, maintainability, and explainability, for both representing and recognizing features.
Many AI models are black boxes today, and leading AI researchers are working to enable model explainability and tunability.
The problem with this proposal is that there is often an inescapable trade-off between explainability and accuracy in AI systems.
Unlike transparency or explainability requirements, this would enable the university to effectively identify any potential flaws without prohibiting the use of complex, proprietary algorithms.
While this could change in the future as research into explainable AI matures — DARPA devoted $75 million in 2017 to this problem — for now, requirements for explainability would come at the cost of accuracy.
The debate about how to make AI safe has ignored the need for a nuanced, targeted approach to regulation, treating algorithmic transparency and explainability like silver bullets without considering their many downsides.
Other features in the new release include improvements to the company's own Cypher database query language and better visualization of the graphs to give more visibility, which is useful for visualizing how machine learning algorithms work, which is known as AI explainability.
As a measure of explainability, we used the number of additional genes, which were needed to connect significant members of a set to a regulatory network.
