240 发简信
FeynmanMa
IP属地：北京
  • RoBERTa, 基于BERT的优化版预训练模型

    Roberta: A robustly optimized bert pretraining approachCitation: 1669 (2...

    5414 0 0
  • Resize,w 360,h 240
    Transformer-XL，处理超级长序列的Transformer

    Transformer-xl: Attentive language models beyond a fixed-length contextC...

    6900 0 0
  • Resize,w 360,h 240
    BERT, 18, 预训练模型

    Bert: Pre-training of deep bidirectional transformers for language under...

    3056 0 0
  • Resize,w 360,h 240
    Transformer, NeurIPS17, Attention is all you need

    Attention Is All You NeedCitation: 26532 (2021-09-04) 1. Motivation 重读经典...

    2784 0 0
  • Resize,w 360,h 240
    MIND, CIKM19, 天猫用户多兴趣表示的召回模型

    Multi-interest network with dynamic routing for recommendation at TmallC...

    2958 0 0
  • Resize,w 360,h 240
    ANIL, ICLR20, 重新审视MAML中的重要部分

    Rapid learning or feature reuse? towards understanding the effectiveness...

    5147 0 0
  • Resize,w 360,h 240
    元学习综述-分类

    Meta-Learning in Neural Networks: A SurveyCitation: 236 (2021-08-29) 1. ...

    3878 0 0
  • 元学习综述-introduction

    Meta-Learning in Neural Networks: A SurveyCitation: 236 (2021-08-29) 1. ...

    1.2 6044 0 5
  • Resize,w 360,h 240
    DRN, WWW18，深度强化学习推荐系统

    DRN: A Deep Reinforcement Learning Framework for News Recommendation Cit...

    5729 0 1
暂无个人介绍