This work presents an experiment-first causal study of training, learning, inference, and feedback in realized neural networks. Across Transformer/Adam, ResNet/SGD momentum, and diffusion U-Net/AdamW systems, the same core relation structure is preserved: realized updates produce receiving-state-dependent nonlinear responses, learning persistently reorganizes distributed functional support, frozen inference recruits training-formed support, and feedback alters subsequent formation states. Only after completing these experiments and cross-system tests did I realize that I had experimentally demonstrated that neural networks are stateful dynamical systems. All protocols, experiments, independent checkers, and archived evidence are publicly available.</p>\n","updatedAt":"2026-08-31T02:01:26.078Z","author":{"_id":"6a928285ec2a5768c8b90e78","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/FdGsPl6I-sDCbVUdtKWJG.png","fullname":"Mian Wang","name":"wind342","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.902256965637207},"editors":["wind342"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/FdGsPl6I-sDCbVUdtKWJG.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.20965","authors":[{"_id":"6a928528073195fee515659e","user":{"_id":"6a928285ec2a5768c8b90e78","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/FdGsPl6I-sDCbVUdtKWJG.png","isPro":false,"fullname":"Mian Wang","user":"wind342","type":"user","name":"wind342"},"name":"Mian Wang","status":"claimed_verified","statusLastChangedAt":"2026-08-29T08:45:04.249Z","hidden":false}],"publishedAt":"2026-08-21T00:00:00.000Z","submittedOnDailyAt":"2026-08-31T00:00:00.000Z","title":"Training, learning and inference: unified dynamics of neural systems","submittedOnDailyBy":{"_id":"6a928285ec2a5768c8b90e78","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/FdGsPl6I-sDCbVUdtKWJG.png","isPro":false,"fullname":"Mian Wang","user":"wind342","type":"user","name":"wind342"},"summary":"We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and relation role. Compiled into a Generation-Fact Graph (GFG), these facts provide an AI-native, compilable scientific fact substrate preserving generation histories. We establish a GFG-based recursive scientific process in which analysis, intervention, replay and validation form facts for later cycles. Using nanoGPT, we establish unified training-learning dynamics. Training is the evolution of a parameter-optimizer system with state and memory: each actual training action enters the receiving state and produces a finite-amplitude nonlinear functional response conditioned by that state and target-specific update geometry. Learning is the persistent reorganization of distributed functional support by these responses; capability formation, maintenance, decline or recovery becomes observable when target-specific states are evaluated against their readout boundaries. Three primary coordinates - target-boundary state, target-specific update geometry and parameter-Adam receiving state - yield a second-order predictor operating before post-update outputs are read. On held-out runs, it achieved 91.43% accuracy and 91.49% macro-averaged recall across four transitions. We further establish inference as a frozen projection of training-learning dynamics. Component gating and rollback show causal recruitment and non-additive combination of query-conditioned support formed during training, deriving organizational conditions realized by Attention. Controlled feedback indicates possible double-edged reinforcement effects. ResNet/CIFAR-100 and diffusion/CIFAR-10 experiments confirm receiving-state-conditioned responses, persistent support reorganization and frozen inference projection beyond nanoGPT.","upvotes":2,"discussionId":"6a928528073195fee515659f","githubRepo":"https://github.com/wind342/gfg-training-learning-inference-experiments","githubRepoAddedBy":"user","ai_summary":"Atomic generation facts compiled into a graph enable recursive scientific processes, and training-learning dynamics in nanoGPT are characterized by state-conditioned parameter updates, persistent functional reorganization, and frozen inference projections validated across architectures.","ai_keywords":["atomic generation fact","Generation-Fact Graph","nanoGPT","parameter-optimizer system","target-specific update geometry","parameter-Adam receiving state","second-order predictor","inference projection","component gating","rollback","Attention","ResNet/CIFAR-100","diffusion/CIFAR-10"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"},{"_id":"6a2da6c8ca070ee12c6e396c","avatarUrl":"/avatars/0355287dcabaa67dbc7f0b10b87451f9.svg","isPro":false,"fullname":"Joe Mama","user":"JoeMama123123123","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"query":{}}">

Cite arxiv.org/abs/2608.20965 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.20965 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.20965 in a Space README.md to link it from this page.