射线演员编程。实现一个分布式参与者框架，该框架在Ray集群上并行化（RL）模型的训练。训练的RL模型将擅长玩月球着陆器游戏。训练RL模型的算法是DQN（深度Q网络）。
Ray actor programming. Implement a distributed actor framework that parallelizes the training of a (RL) model on a Ray cluster. The RL model that trained will excel in playing the game of Lunar Lander. The algorithm to train the RL model is DQN (Deep Q-Network). (2024-03-18, Jupyter Notebook, 0KB, 下载0次)
该项目是关于使用机器学习和自然语言处理方法来分析新闻文章的数据集，这些文章被分为五个类别：政治、体育、科技、娱乐和商业。目标是构建能够根据新文章的内容准确地为其分配标签的模型。
The project is about using machine learning and natural language processing methods to analyze a dataset of news articles that are classified into five categories: politics, sport, tech, entertainment, and business. The objective is to build models that can accurately assign labels to new articles based on their content. (2024-02-07, Jupyter Notebook, 0KB, 下载0次)
这个基于Python的项目分析来自流亡之路（PoE）的贸易数据。它利用数据分析、可视化和预测建模，基于各种属性提供对商品价格变化的见解。该工具旨在帮助玩家做出明智的交易决策，并了解市场动态。
This Python-based project analyzes trade data from Path of Exile (PoE). It offers insights into item price variations based on various attributes, employing data analysis, visualization, and predictive modeling. The tool is designed to help players make informed trading decisions and to understand market dynamics. (2024-01-06, Jupyter Notebook, 0KB, 下载0次)
AB测试报告的自动报告包括预测试和后测试。自动报告包含样本量计算、测试持续时间计算、计算效果大小、执行AA测试、AB测试、正态性检查、均匀性检查、新颖性效果测试、卡方检验等方法。
Auto report of AB testing report includes both pretest and post-test. The auto report contains methods for sample size calculation, test duration calculation, calculating effect size, performing AA test, AB test, Normality check, Homogenity check, Novelty effect test, Chi-square tests, and more. (2023-12-28, Jupyter Notebook, 0KB, 下载0次)
使用梯度提升分类器的泰坦尼克Kaggle竞赛TOP13%解决方案。此外，实现Streamlit应用程序以与模型一起玩。
TOP13% solution for the Titanic-Kaggle competition using a Gradient Boosting Classifier. Moreover, implementation of a Streamlit App to play with the models. (2023-09-11, Jupyter Notebook, 0KB, 下载0次)
深度井字游戏，使用深度强化学习来训练深度神经网络来玩井字游戏并使用tensorflow.js进行部署。
deep-tic-tac-toe,Used deep reinforcement learning to train a deep neural network to play tic- tac-toe and deployed using tensorflow.js. (2022-06-13, Jupyter Notebook, 743KB, 下载0次)
单词链游戏，单词链是一个与计算机（AI Word Repo）对抗的游戏，你说一个单词，下一个玩家说一个词...
Word chain is a game to play against the Computer(AI/Word Repo) where you say a word and the next player says a word starting with the last letter of the previous word said, you cannot repeat the word or mispronounce. (2021-09-06, Jupyter Notebook, 6KB, 下载0次)
本研究的目的是根据学习者的学习轨迹来预测他们的学习风格。我们分析了通过斯坦福大学的Logunita平台管理的edX课程“统计学习”（2015年冬季和2016年冬季）中收集的数据
The objective of this study is to predict learners’ learning styles based on
their learning traces. we analyzed data collected from the edX course
“Statistical Learning" session Winter 2015 and Winter 2016), administered via
Stanford’s Logunita platform
, (2021-01-11, Jupyter Notebook, 4632KB, 下载0次)
斯坦福-阿佩尔实验室-药物动力学研究项目：药物动力学数据建模和可视化工具。药物递送研究的主要用途。Python支持文件和用于配置自定义PK分析的示例Jupyter Notebook
Stanford Appel Lab - Study Pharmacokinetics Project: Pharmacokinetic data
modeling and visualization tool. Primary usage for drug delivery studies.
Python supporting files and an example Jupyter Notebook for configuring custom
PK analysis
, (2021-02-20, Jupyter Notebook, 30KB, 下载0次)