{
    "byline": null,
    "dir": null,
    "excerpt": "This paper builds on what we learned in \u201cUnderstanding deep learning requires rethinking generalization\u201d. In that paper they showed that DNNs are able to fit pure noise in the same amount of time as it can fit real data, which means that our optimization algorithm (SGD, Adam, etc.) is not what\u2019s keeping DNNs from overfitting.",
    "length": 4325,
    "siteName": null,
    "title": "A closer look at memorization in deep networks"
}