Artificial intelligence (AI) is proving very adept at certain tasks like inventing human faces that don’t exist, or winning games of poker – but these networks still struggle when it comes to something humans do naturally: imagine.
To try and unlock AI’s capacity for imagination, researchers have come up with a new method for enabling AI systems to work out what an object should look like, even if they’ve never actually seen one exactly like it before.
“Humans can separate their learned knowledge by attributes – for instance, shape, pose, position, color – and then recombine them to imagine a new object.
What the team has come up with here is called controllable disentangled representation learning, and it uses an approach similar to those used to create deepfakes – disentangling different parts of a sample (so separating face movement and face identity, in the case of a deepfake video).
It means that if an AI sees a red car and a blue bike, it will then be able to ‘imagine’ a red bike for itself.
The researchers have put this together in a framework they’re calling Group Supervised Learning.
The same approach could also be applied in the fields of medicine and self-driving cars, the researchers say, with AI able to ‘imagine’ new drugs, or visualize new road scenarios that it hasn’t been specifically trained for in the past.
“Deep learning has already demonstrated unsurpassed performance and promise in many domains, but all too often this has happened through shallow mimicry, and without a deeper understanding of the separate attributes that make each object unique.”