Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Last revision Both sides next revision
encoder_decoder [2018/04/26 01:42]
admin
encoder_decoder [2018/08/23 07:14]
admin
Line 57: Line 57:
 context and passage pairs to and from another language as a way of paraphrasing the questions context and passage pairs to and from another language as a way of paraphrasing the questions
 and contexts. and contexts.
 +
 +https://​arxiv.org/​abs/​1808.07233 Neural Architecture Optimization
 +
 +We call this new approach neural architecture optimization (NAO). There are three key components in our proposed approach: (1) An encoder embeds/maps neural network architectures into a continuous space. (2) A predictor takes the continuous representation of a network as input and predicts its accuracy. (3) A decoder maps a continuous representation of a network back to its architecture. ​