How explainable artificial intelligence can help humans innovate
AI algorithms can solve hard problems and learn incredible tasks, but they can't explain how they do these things. If researchers can build explainable AI, it could lead to a flood of new knowledge.
More from The Conversation
Climate scientists: concept of net zero is a dangerous trap
Prominent academics, including a former IPCC chair, round on governments worldwide for using the concept of net zero emissions to 'greenwash' their lack of commitment to solving global warming.
«The only way to keep humanity safe is the immediate and sustained radical cuts to greenhouse gas emissions in a socially just way.»
If all the vehicles in the world were to convert to electric, would it be quieter?
Noise pollution is a serious problem, and cars make a lot of it. But roads are also a factor.
How to break unhealthy habits: Stop obsessing over willpower and focus on routines
Understanding and changing the environment in which habits form is a critical step when it comes to breaking unwanted behaviors and forming healthy ones.
«Instead, we concoct more compelling explanations, like saying we drink coffee to ease our morning fog.»
Slime is all around and inside you – new research on its origins offers insight into genetic evolution
A vast array of species, including people, use slime for a variety of essential bodily functions. Studying the genetic ancestry of slime surprisingly showcases the role of repetitive DNA in evolution.
These high school ‘classics’ have been taught for generations
An English professor takes a critical look at why today’s students are assigned the same books that were assigned decades ago – and why American school curricula are so difficult to change.