less than 1 minute read

1 综述

2 理论

3 神经网络搜索

3.1 通用网络

  1. EENA: Efficient Evolution of Neural Architecture
    2019-05-10 paper
    EENA:具有导向性地神经网络自动搜索;

  2. Multinomial Distribution Learning for Effective Neural Architecture Search
    2019-05-18 paper

3.2 分割网络

  1. Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
    CVPR 2019 2018-10-28 paper
    $\bullet \bullet$

4 改进

4.1 损失函数设计

  1. AM-LFS: AutoML for Loss Function Search
    2019-05-17 paper
    使用强化学习自动设计损失函数

4.2 加速

  1. Searching for A Robust Neural Architecture in Four GPU Hours
    CVPR 2019 改进版 2019-10-10 paper | pytorch-official

TOP

Comments