Ashish Patel 🇮🇳’s Post

Day-41 Computer Vision Learning ENAS — Efficient Neural Architecture Search via Parameter Sharing (Image Classification) by Google Brain Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2018 #ICML, which has already got over 1113 citations. 🔸 ENAS constructs a large computational graph, where each subgraph represents a neural network architecture, hence forcing all architectures to share their parameters. 🔸 Sharing parameters among child models allows ENAS to deliver strong empirical performances, whilst using much fewer GPU-hours than existing automatic model design approaches. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/es6s4QJ official Code : https://bit.ly/3708S29 tensorflow: https://bit.ly/3rIWvPB pytorch: https://bit.ly/2MQNOUM keras: https://bit.ly/2OjVkrv ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 This architecture use Representing Search Space as A Single Directed Acyclic Graph (DAG) 🔸 LSTM is used as controller Network. 🔸 It is also Design Recurrent cells and Convolution cells #computervision #artificialintelligence #innovation