Developments in artificial intelligence often draw inspiration from how humans think, but now AI has turned the tables to teach us about how brains learn.
Juan Carlos Izpisua Belmonte and David Markowitz's latest study finds that an artificial neural network, or "neural network," created by the duo, can predict a person's neural activity based on vocal tone.
The system uses a brain-like multi-layer network to analyze a person's voice in real time, delivering a more accurate result than the person's own vocal tics.
The team tested their neural network on 22 people of varied ages and backgrounds. When trying to identify whether or not people are lying, the system correctly identified 60 percent of lies with 97 percent accuracy.
Juan Carlos Izpisua Belmonte and David Markowitz's latest study finds that an artificial neural network, or "neural network," created by the duo, can predict a person's neural activity based on vocal tone.
The system uses a brain-like multi-layer network to analyze a person's voice in real time, delivering a more accurate result than the person's own vocal tics.
The team tested their neural network on 22 people of varied ages and backgrounds. When trying to identify whether or not people are lying, the system correctly identified 60 percent of lies with 97 percent accuracy.
