Day-42 Computer Vision Learning PNASNet — Progressive Neural Architecture Search (Image Classification) by Johns Hopkins University, Google AI, and Stanford University Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2018 #ECCV, which has already got over 931 citations. 🔸 Fewer Compute for Searching Models Compared With NASNet. Outperforms SENet, NASNet-A, and AmoebaNets under the same model capacity. 🔸 A sequential model-based optimization (SMBO) strategy is used such that a surrogate model is learnt to guide the search through structure space. 🔸 Direct comparison under the same search space shows that PNASNet is up to 5 times more efficient than the Reinforcement Learning (RL) method, 8 times faster in terms of total compute. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e_PTYdj official Code : https://bit.ly/3tMQ7bX tensorflow: https://bit.ly/3jCVm9A pytorch: https://bit.ly/2NldQza keras: https://bit.ly/3a82qbe ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 This Algo is based on reinforcement learning and evolutionary algorithms. #computervision #artificialintelligence #technology
Thank you for sharing!
🔸 This architecture use cell topologies. 🔸 The method in this paper uses a sequential model-based optimization (SMBO) strategy, in which the structure is searched in order of increasing complexity, while the agent model is learned to guide the structure space search. #deeplearning #machinelearning #innovation For previous post visit this github : https://github.com/ashishpatel26/365-Days-Computer-Vision-Learning-Linkedin-Post
This looks very interesting Thank you for sharing