VIP20

本课程属于：005-Artificial Intelligence and Machine Learning Engineering English Technical Courses · 共 20 门相关课程，组合学习更完整。

查看所属VIP全部课程 →

← 返回所属目录咨询 / 购买

Applied Machine Learning Systems with Python and Real-World Datasets

30 Chapters

View Course Samples Online

Course overview

applied ML systems, Python ecosystem, real-world dataset challenges, and end-to-end workflow.

ecosystemreal-world

Python environment and tooling

virtual environments, package management, Jupyter, IDEs, and reproducibility practices.

environmentenvironments

Data acquisition and ingestion

APIs, web scraping, databases, CSV/JSON/Parquet, and streaming sources.

acquisitioningestion

Exploratory data analysis and visualization

pandas, matplotlib, seaborn, plotly, and profiling large datasets.

Exploratoryanalysis

Data cleaning and preprocessing

missing values, outliers, encoding, scaling, and pipeline construction with scikit-learn.

cleaningpreprocessing

Feature engineering and selection

domain-driven features, transformations, dimensionality reduction, and feature stores.

selectiondomain-driven

Supervised learning fundamentals

regression and classification with scikit-learn, model evaluation, and cross-validation.

Supervisedregression

Tree-based models and ensembles

random forests, gradient boosting, XGBoost, LightGBM, and hyperparameter tuning.

Tree-basedensembles

Unsupervised learning

clustering, anomaly detection, and dimensionality reduction for real-world data.

Unsupervisedclustering

Time series analysis and forecasting

stationarity, ARIMA, Prophet, and feature-based approaches.

analysisforecasting

Natural language processing

text preprocessing, vectorization, embeddings, and transformer-based models.

languageprocessing

Computer vision

image preprocessing, augmentation, CNNs, transfer learning, and object detection.

Computerpreprocessing

Model evaluation and validation

metrics, ROC/AUC, precision-recall, calibration, and statistical significance.

evaluationvalidation

Hyperparameter optimization and AutoML

grid search, random search, Bayesian optimization, and neural architecture search.

Hyperparameteroptimization

Model interpretability and explainability

SHAP, LIME, partial dependence, and fairness auditing.

interpretabilityexplainability

MLOps fundamentals

CI/CD for ML, model versioning, experiment tracking, and model registries.

Deployment patterns

batch, real-time, and streaming inference; REST APIs, gRPC, and serverless.

Deploymentpatterns

Scaling ML systems

distributed training, data parallelism, model parallelism, and GPU acceleration.

distributedtraining

Monitoring and maintenance

data drift, concept drift, performance monitoring, and retraining strategies.

Monitoringmaintenance

Data privacy and security

differential privacy, federated learning, encryption, and secure multi-party computation.

securitydifferential

bias detection, fairness metrics, transparency, and ethical considerations in production.

Responsibledetection

predictive maintenance using sensor data from industrial equipment.

predictivemaintenance

customer churn prediction with tabular data and imbalanced classes.

customerprediction

fraud detection in financial transactions with streaming data.

detectionfinancial

recommendation systems for e-commerce using collaborative filtering and content-based methods.

recommendatione-commerce

medical image classification for diagnosis support.

classificationdiagnosis

demand forecasting for retail supply chain optimization.

forecastingoptimization

sentiment analysis on social media data for brand monitoring.

sentimentanalysis

anomaly detection in network intrusion detection systems.

detectionintrusion

Capstone project

design, build, and deploy an end-to-end ML system on a real-world dataset.

Capstoneend-to-end