Machine Learning
机器学习是数据科学的核心应用课程，涵盖监督学习、无监督学习与强化学习三大范式。主要内容包括线性回归、逻辑回归、决策树、支持向量机、神经网络、聚类、降维与集成学习等算法。课程结合Scikit-learn、TensorFlow或PyTorch框架，训练学生从数据预处理、特征工程、模型训练到评估部署的完整流程，理解过拟合、正则化、交叉验证等关键概念。
Machine Learning is a core applied course in data science, covering supervised, unsupervised, and reinforcement learning paradigms. Topics include linear regression, logistic regression, decision trees, support vector machines, neural networks, clustering, dimensionality reduction, and ensemble methods. Using Scikit-learn, TensorFlow, or PyTorch, students train through the complete workflow from data preprocessing and feature engineering to model training, evaluation, and deployment, understanding key concepts like overfitting, regularization, and cross-validation.
基于真实房屋交易数据集，完成特征工程、模型选择、调参与评估，对比多种算法表现，最终部署预测模型并撰写技术报告，分析模型可解释性。
Based on a real housing transaction dataset, complete feature engineering, model selection, tuning, and evaluation, compare multiple algorithms, deploy the prediction model, and write a technical report analyzing model interpretability.