{"ID":2898040,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.03885","arxiv_id":"2507.03885","title":"Unraveling the Black Box of Neural Networks: A Dynamic Extremum Mapper","abstract":"We point out that neural networks are not black boxes, and their generalization stems from the ability to dynamically map a dataset to the extrema of the model function. We further prove that the number of extrema in a neural network is positively correlated with the number of its parameters. We then propose a new algorithm that is significantly different from back-propagation algorithm, which mainly obtains the values of parameters by solving a system of linear equations. Some difficult situations, such as gradient vanishing and overfitting, can be simply explained and dealt with in this framework.","short_abstract":"We point out that neural networks are not black boxes, and their generalization stems from the ability to dynamically map a dataset to the extrema of the model function. We further prove that the number of extrema in a neural network is positively correlated with the number of its parameters. We then propose a new algo...","url_abs":"https://arxiv.org/abs/2507.03885","url_pdf":"https://arxiv.org/pdf/2507.03885v3","authors":"[\"Shengjian Chen\"]","published":"2025-07-05T03:54:37Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"stat.ML\"]","methods":"[]","has_code":false}