[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-neural-networks":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"354b3df3-8bb3-4b56-9761-e9bd1b362c5f","neural networks","neural-networks",2,null,[11,20,27],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"e0d15783-0618-4214-b5ce-5fee2e4d56b4","multi-fidelity-models-composite-mechanics-en","Multi-fidelity models for composite mechanics","A review of co-kriging, deep Gaussian processes, and neural nets for cheaper composite-mechanics prediction.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777962656813-ewau.png","en","2026-05-05T06:30:42.408909+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"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.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774939851239-stpu.png","2026-03-31T06:01:01.08842+00:00",{"id":28,"slug":29,"title":30,"summary":31,"category":16,"image_url":32,"cover_image":32,"language":18,"created_at":33},"6954fa2b-8b66-4839-884b-e46f89fa1bc3","adaptive-block-scaled-data-types-en","IF4: Smarter 4-Bit Quantization That Adapts to Your Data","MIT researchers propose a hybrid data format that switches between floating-point and integer representations, improving accuracy in 4-bit neural network quantization.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774939577640-6i9x.png","2026-03-31T06:00:36.65963+00:00"]