Neural Architecture Search with Reinforcement Learning

5 Nov 2016 Barret Zoph Quoc V. Le

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 Neural Architecture Search Percentage correct 96.4 # 37
Neural Architecture Search CIFAR-10 Image Classification NASNet-A + c/o Percentage error 2.40 # 9
Params 27.6M # 12
Language Modelling Penn Treebank (Character Level) NASCell Bit per Character (BPC) 1.214 # 10
Number of params 16.3M # 2
Language Modelling Penn Treebank (Word Level) NAS Cell Test perplexity 64.0 # 29
Params 25M # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet