[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-representation-learning":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"ac67e4a6-32cb-44bc-9aea-a6afe5b83ec1","representation learning","representation-learning",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"bffe6d87-1e52-49cc-8fb7-bb5776889b14","understanding-neural-nets-metric-similarity-en","Geometry Matters: Understanding Neural Networks Through Manifolds","Researchers use Riemannian geometry to analyze the intrinsic structure of neural network representations, revealing patterns hidden by traditional similarity metrics.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774939851239-stpu.png","en","2026-03-31T06:01:01.08842+00:00"]