Recommendable! Another, very interesting paper by Alphabet/Google/Deepmind researchers.
"... These flexible biases allow our model to surpass the previous neuro-symbolic state-of-the-art using less than 60% of available labelled data. Together, these results refute the neuro-symbolic thesis laid out by previous work involving these datasets, and they provide evidence that neural networks can indeed learn to reason effectively about the causal, dynamic structure of physical events. ..."
No comments:
Post a Comment