{"id":94555,"date":"2025-08-25T11:38:14","date_gmt":"2025-08-25T11:38:14","guid":{"rendered":"https:\/\/www.newsbeep.com\/au\/94555\/"},"modified":"2025-08-25T11:38:14","modified_gmt":"2025-08-25T11:38:14","slug":"pong-cloned-by-neural-network","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/au\/94555\/","title":{"rendered":"Pong Cloned By Neural Network"},"content":{"rendered":"<p>Although not the first video game ever produced, Pong was the first to achieve commercial success and has had a tremendous influence on our culture as a whole. In Pong\u2019s time, its popularity ushered in the arcade era that would last for more than two decades. Today, it retains a similar popularity partially for approachability: gameplay is relatively simple, has hardwired logic, and provides insights about the state of computer science at the time. For these reasons, [Nick Bild] has decided to recreate this arcade classic, but not in a traditional way. <a href=\"https:\/\/hackaday.io\/project\/203863-i-cloned-pong-with-a-neural-network\" target=\"_blank\" rel=\"nofollow noopener\">He\u2019s trained a neural network to become the game instead<\/a>.<\/p>\n<p>To train this neural network, [Nick] used hundreds of thousands of images of gameplay. Much of it was real, but he had to generate synthetic data for rare events like paddle misses. The system is a transformer-based network with separate branches for predicting the movements of the ball, taking user input, and predicting paddle motion. A final branch is used to integrate all of these processes. To play the game, the network receives four initial frames and predicts everything from there.<\/p>\n<p>From the short video linked below, the game appears to behave indistinguishably from a traditionally coded game. Even more impressive is that, due to [Nick]\u2019s lack of a GPU, the neural network itself was trained using only a pair of old Xeon processors. He\u2019s pretty familiar with functionally useful AI as well. <a href=\"https:\/\/hackaday.com\/2024\/05\/15\/generative-ai-hits-the-commodore-64\/\" rel=\"nofollow noopener\" target=\"_blank\">He recently built a project that uses generative AI running on an 80s-era Commodore<\/a> to generate images in a similar way to modern versions, just with slightly fewer pixels.<\/p><\/p>\n","protected":false},"excerpt":{"rendered":"Although not the first video game ever produced, Pong was the first to achieve commercial success and has&hellip;\n","protected":false},"author":2,"featured_media":94556,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":{"0":"post-94555","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-au","12":"tag-australia","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/94555","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=94555"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/94555\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/94556"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=94555"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=94555"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=94555"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}