{"id":127814,"date":"2021-09-18T13:22:57","date_gmt":"2021-09-18T20:22:57","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2021\/09\/google-ai-introduces-two-new-families-of-neural-networks-called-efficientnetv2-and-coatnet-for-image-recognition"},"modified":"2021-09-18T13:22:57","modified_gmt":"2021-09-18T20:22:57","slug":"google-ai-introduces-two-new-families-of-neural-networks-called-efficientnetv2-and-coatnet-for-image-recognition","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2021\/09\/google-ai-introduces-two-new-families-of-neural-networks-called-efficientnetv2-and-coatnet-for-image-recognition","title":{"rendered":"Google AI Introduces Two New Families of Neural Networks Called \u2018EfficientNetV2\u2019 and \u2018CoAtNet\u2019 For Image Recognition"},"content":{"rendered":"

<\/a><\/p>\n

Training efficiency has become a significant factor for deep learning as the neural network models, and training data size grows. GPT-3<\/a> is an excellent example to show how critical training efficiency factor could be as it takes weeks of training with thousands of GPUs to demonstrate remarkable capabilities in few-shot learning.<\/p>\n

To address this problem, the Google AI team introduce two families of neural networks for image recognition. First is EfficientNetV2<\/a>, consisting of CNN (Convolutional neural networks) with a small-scale dataset for faster training efficiency such as ImageNet1k<\/a> (with 1.28 million images). Second is a hybrid model called CoAtNet<\/a>, which combines convolution<\/a> and self-attention<\/a> to achieve higher accuracy on large-scale datasets such as ImageNet21<\/a> (with 13 million images) and JFT<\/a> (with billions of images). As per the research report by Google, EfficientNetV2<\/a> and CoAtNet<\/a> both are 4 to 10 times faster while achieving state-of-the-art and 90.88% top-1 accuracy on the well-established ImageNet<\/a> dataset.<\/p>\n","protected":false},"excerpt":{"rendered":"

Training efficiency has become a significant factor for deep learning as the neural network models, and training data size grows. GPT-3 is an excellent example to show how critical training efficiency factor could be as it takes weeks of training with thousands of GPUs to demonstrate remarkable capabilities in few-shot learning. To address this problem, [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-127814","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/127814","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/396"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=127814"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/127814\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=127814"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=127814"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=127814"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}