{"id":197423,"date":"2024-10-10T23:24:58","date_gmt":"2024-10-11T04:24:58","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2024\/10\/overcoming-catastrophic-forgetting-algorithm-inspired-by-brain-allows-neural-networks-to-retain-knowledge"},"modified":"2024-10-10T23:24:58","modified_gmt":"2024-10-11T04:24:58","slug":"overcoming-catastrophic-forgetting-algorithm-inspired-by-brain-allows-neural-networks-to-retain-knowledge","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2024\/10\/overcoming-catastrophic-forgetting-algorithm-inspired-by-brain-allows-neural-networks-to-retain-knowledge","title":{"rendered":"Overcoming \u2018catastrophic forgetting\u2019: Algorithm inspired by brain allows neural networks to retain knowledge"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/overcoming-catastrophic-forgetting-algorithm-inspired-by-brain-allows-neural-networks-to-retain-knowledge2.jpg\"><\/a><\/p>\n<p>Neural networks have a remarkable ability to learn specific tasks, such as identifying handwritten digits. However, these models often experience \u201ccatastrophic forgetting\u201d when taught additional tasks: They can successfully learn the new assignments, but \u201cforget\u201d how to complete the original. For many artificial neural networks, like those that guide self-driving cars, learning additional tasks thus requires being fully reprogrammed.<\/p>\n<p>Biological brains, on the other hand, are remarkably flexible. Humans and animals can easily learn how to play a new game, for instance, without having to re-learn how to walk and talk.<\/p>\n<p>Inspired by the flexibility of human and animal brains, Caltech researchers have now developed a new type of <a href=\"https:\/\/techxplore.com\/tags\/algorithm\/\" rel=\"tag\" class=\"\">algorithm<\/a> that enables neural networks to be continuously updated with new data that they are able to learn from without having to start from scratch. The algorithm, called a functionally invariant path (FIP) algorithm, has wide-ranging applications from improving recommendations on online stores to fine-tuning self-driving cars.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Neural networks have a remarkable ability to learn specific tasks, such as identifying handwritten digits. However, these models often experience \u201ccatastrophic forgetting\u201d when taught additional tasks: They can successfully learn the new assignments, but \u201cforget\u201d how to complete the original. For many artificial neural networks, like those that guide self-driving cars, learning additional tasks thus [\u2026]<\/p>\n","protected":false},"author":359,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,41,6,1491],"tags":[],"class_list":["post-197423","post","type-post","status-publish","format-standard","hentry","category-biological","category-information-science","category-robotics-ai","category-transportation"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/197423","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\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=197423"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/197423\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=197423"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=197423"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=197423"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}