DeepMind takes a shot at teaching AI to reason with relational networks

The latest paper by DeepMind, Alphabet's British AI outfit, attempts to enable machines to reason by tacking on RNs to convolutional neural networks and recurrent neural networks, both traditionally used for computer vision and natural language processing. "It is not that deep learning is unsuited to reasoning tasks – more that the correct deep learning architectures, or modules, did not exist to enable general relational reasoning. "State-of-the-art results on CLEVR using standard visual question answering architectures are 68.5 per cent, compared to 92.5 per cent for humans. The RN managed to pass 18 out of 20 tasks, beating previous attempts that used memory networks used by Facebook and DeepMind's differentiable neural computer.