Our new work on memory uses a neural network's weights as fast and compressive associative storage. Reading from the memory is performed by approximate minimisation of the energy modelled by the network. https://t.co/AS64VqSAjD pic.twitter.com/6uPAD9asgv
— DeepMind (@DeepMindAI) October 21, 2019
from Twitter https://twitter.com/DeepMindAI
October 21, 2019 at 06:42AM
via IFTTT
No comments:
Post a Comment