←搜索结果

搜索“GitHub”

按匹配度 · 共 1663 条结果 清除搜索

星期日

  1. Lilian Weng：Lil'Log

    策略梯度算法详解 | Lil'Log

    Lil'Log 发布《策略梯度算法》一文，系统讲解策略梯度这一强化学习求解思路：直接对参数化策略 πθ(a|s) 建模并优化，用梯度上升最大化奖励目标 J(θ)。文章给出策略梯度定理的完整证明，说明它如何避开状态分布 dπ(.) 的导数、简化 ∇θJ(θ) 的计算，并指出原始策略梯度更新无偏但方差高，后续算法多围绕降方差展开。

    same type may vary a lot across multiple robots. Batch normalization is applied to fix it by normalizing every dimension across samples in one minibatch. D4PG [paper|code (Search “github d4pg” and you will see a few.)] Distributed Distributional DDPG (D4PG) applies a set of improvements on DDPG to make it run in the distributional fashion. (1) Distributional Critic: The critic estimates the expected Q value as a random variable a distribution $Z w$ parameterized by $w$ and therefore $Q w(s, a) =

    匹配字段正文

    #analysis#教程/实践#推理

星期六

  1. Lilian Weng：Lil'Log

    用 RNN 预测股票价格（第二部分）：多股票预测与嵌入向量

    Lilian Weng 在教程第二部分中扩展了第一部分构建的 RNN，使其能同时处理多只股票。模型用股票代码的嵌入向量（embedding_size × stock_count）替代 one-hot 编码，与每日价格向量拼接后输入 LSTM，训练集与测试集按每只股票 90%/10% 划分。

    folder. TensorBoard will read this file during startup. The model is trained with top 50 stocks with largest market values in the S&P 500 index. (Run the following command within github.com/lilianweng/stock-rnn) And the following configuration is used: Price Prediction As a brief overview of the prediction quality, Fig. 3 plots the predictions for test data of “KO”, “AAPL”, “GOOG” and “NFLX”. The overall trends matched up between the true values and the predictions. Considering how the predicti

    匹配字段正文

    #analysis#教程/实践#数据/训练

星期三

  1. Lilian Weng：Lil'Log

    面向好奇者的深度学习概览：从 AlphaGo 到 CNN 与 RNN

    Lilian Weng 在 WiMLDS x Fintech meetup 演讲整理的文章中，以 2016 年 AlphaGo 以 1-4 击败九段李世石为引，解释深度学习为何在当下兴起：数据量大幅增长与算力显著提升，使深层神经网络能自动学习复杂非线性特征。文章随后介绍了 CNN（受视觉皮层 V1/V2/V4 启发，含 Residual Net）与 RNN 两类经典模型及其在语音识别、机器翻译等任务中的应用。

    open source toolkits and libraries for building deep learning models. Tensorflow is fairly new but has attracted a lot of popularity. It turns out, TensorFlow was the most forked Github project of 2015. All that happened in a period of 2 months after its release in Nov 2015. If you are very new to the field and willing to devote some time to studying deep learning in a more systematic way, I would recommend you to start with the book Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Cou

    匹配字段正文

    #analysis#教程/实践#数据/训练