![An architecture that combines deep neural networks and vector-symbolic models An architecture that combines deep neural networks and vector-symbolic models](https://search.ai.wiki/wp-content/uploads/2023/03/an-architecture-that-combines-deep-neural-networks-and-vector-symbolic-models.jpg)
An architecture that combines deep neural networks and vector-symbolic models
Researchers at IBM Research Zürich and ETH Zürich have recently created a new architecture that combines two of the most renowned artificial intelligence approaches, namely deep neural networks and vector-symbolic models. Their architecture, presented in Nature Machine Intelligence, could overcome the limitations of both these approaches, solving progressive matrices and other reasoning tasks more effectively.