zoukankan      html  css  js  c++  java
  • 优化算法动画演示Alec Radford's animations for optimization algorithms

    Alec Radford has created some great animations comparing optimization algorithms SGDMomentumNAGAdagradAdadelta,RMSprop (unfortunately no Adam) on low dimensional problems. Also check out his presentation on RNNs.

    "Noisy moons: This is logistic regression on noisy moons dataset from sklearn which shows the smoothing effects of momentum based techniques (which also results in over shooting and correction). The error surface is visualized as an average over the whole dataset empirically, but the trajectories show the dynamics of minibatches on noisy data. The bottom chart is an accuracy plot."
    "Beale's function: Due to the large initial gradient, velocity based techniques shoot off and bounce around - adagrad almost goes unstable for the same reason. Algos that scale gradients/step sizes like adadelta and RMSProp proceed more like accelerated SGD and handle large gradients with more stability."
    "Long valley: Algos without scaling based on gradient information really struggle to break symmetry here - SGD gets no where and Nesterov Accelerated Gradient / Momentum exhibits oscillations until they build up velocity in the optimization direction. Algos that scale step size based on the gradient quickly break symmetry and begin descent."
    "Saddle point: Behavior around a saddle point. NAG/Momentum again like to explore around, almost taking a different path. Adadelta/Adagrad/RMSProp proceed like accelerated SGD."
     
    from: http://www.denizyuret.com/2015/03/alec-radfords-animations-for.html
  • 相关阅读:
    Centos系统安装
    HPDL380G8平台11.2.0.3 RAC实施手册
    bash的位置变量和特殊变量
    bash中的算术运算
    bash文本查看及处理工具
    bash快捷键及输入输出重定向
    bash文件名统配
    文本搜索grep知识点总结
    sed练习
    流编辑器sed知识点总结
  • 原文地址:https://www.cnblogs.com/GarfieldEr007/p/5328618.html
Copyright © 2011-2022 走看看