Self-learning AI emulates the human brain

Achievements

European researchers have designed brain-like artificial neural networks capable of numerical and spatial cognition and written language processing without any explicit training or pre-programming. Their work, based on the machine-learning approach of generative models, significantly advances the development of self-learning artificial intelligence, while also deepening understanding of human cognition.

Date:

22/07/2016 - 17:25

The research was led by Marco Zorzi at the University of Padova and funded by to a starting grant from the European Research Centre (ERC). The project – GENMOD – demonstrated that it is possible to build an artificial neural network that observes the world and generates its own internal representation based on sensory data. For example, the network was able by itself to develop approximate number sense, the ability to determine basic numerical qualities, such as greater or lesser, without actually understanding the numbers themselves, just like human babies and some animals.

Read more

GENMOD

Project:

Generative Models of Human Cognition

Author

Anonymous (not verified)

Xtranet-ISA