首页
学习
活动
专区
圈层
工具
发布
    • 综合排序
    • 最热优先
    • 最新优先
    时间不限
  • 来自专栏AutoML(自动机器学习)

    通过损失函数优化提高训练速度、准确性和数据利用率

    Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization 简介 该论文的主要贡献是提出了Genetic Loss-function

    1.1K10发布于 2021-01-29
  • 来自专栏AI研习社

    开发 | Facebook 开源深度学习推荐模型 DLRM,可直接用 PyTorch 和 Caffe2 实现!

    /input/kaggle_processed.npz --loss-function=bce --round-targets=True --learning-rate=0.1 --mini-batch-size

    1K30发布于 2019-07-12
  • 来自专栏专知

    【论文推荐】最新七篇图像检索相关论文—草图、Tie-Aware、场景图解析、叠加跨注意力机制、深度哈希、人群估计

    instance similarity, a weighted cross-entropy loss and a minimum mean square error loss are tailored for loss-function

    1.3K30发布于 2018-06-05
  • 来自专栏机器之心

    想知道Facebook怎样做推荐?FB开源深度学习推荐模型

    /input/kaggle_processed.npz --loss-function=bce --round-targets=True --learning-rate=0.1 --mini-batch-size

    93210发布于 2019-07-12
  • 来自专栏相约机器人

    Facebook 开源深度学习推荐模型 DLRM,可直接用 PyTorch 和 Caffe2 实现!

    /input/kaggle_processed.npz --loss-function=bce --round-targets=True --learning-rate=0.1 --mini-batch-size

    1.5K10发布于 2019-07-12
  • 来自专栏CVer

    [计算机视觉论文速递] 2018-03-11

    instance similarity, a weighted cross-entropy loss and a minimum mean square error loss are tailored for loss-function

    1.1K80发布于 2018-04-12
  • 来自专栏CreateAMind

    论文梳理关系图:Neural Symbolic and Probabilistic Logic Papers

    Paper This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function

    55021编辑于 2023-09-12
  • 来自专栏arXiv每日学术速递

    自然语言处理学术速递[6.25]

    several other more sophisticated methods of such mapping including, several auto-encoder based and custom loss-function

    86820发布于 2021-07-02
  • 来自专栏arXiv每日学术速递

    人工智能学术速递[7.23]

    This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function

    91920发布于 2021-07-27
  • 来自专栏arXiv每日学术速递

    自然语言处理学术速递[12.14]

    Hence, we propose a structure-aware Mutual Information based loss-function DMI (Discourse Mutual Information

    93120编辑于 2021-12-17
  • 来自专栏arXiv每日学术速递

    机器学习学术速递[7.23]

    This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function

    1.3K40发布于 2021-07-27
  • 来自专栏arXiv每日学术速递

    机器学习学术速递[6.25]

    several other more sophisticated methods of such mapping including, several auto-encoder based and custom loss-function

    2.2K20发布于 2021-07-02
领券