Conversation

Edward Grefenstette 🇪🇺 @egrefen@mastodon.social
@egrefen
And now, for something a little different… arxiv.org/abs/1711.04574 We show that robust, interpretable latent rules can be synthesised by backprop. Data efficient, good generalisation. Can be trained end-to-end within a larger neural network. Upcoming in JAIR. w/ @LittleBimble
arxiv.org
Learning Explanatory Rules from Noisy Data
Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity...
3
135