AI Systems
Description: In our last lecture, we will explore the deployment process of ML models. Once models are trained, we need to deploy them as part of larger systems to be used (i.e., AI Systems). We will show the challenges that motivate our focus on this stage and present different alternatives for efficient AI systems deployment.Department: Centro de Estudios y Asesorías en Estadística (CEASE)
Institution: Universidad de Nariño
Date: July 19, 2025
Hours: 4
From: 10:00 am
To: 12:00 am
Resources
Books
- Kleppmann, M. (2017). Designing Data-Intensive Applications. O’Reilly Media
- Huyen, C. (2022). Designing Machine Learning Systems. O’Reilly Media
Papers and Reports
- Sculley, D., et al. (2015). Hidden technical debt in machine learning systems
- Breck, E., et al. (2016). The ML test score: A rubric for ML production readiness and technical debt reduction
- Paleyes, A., et al. (2020). Challenges in deploying machine learning: a survey of case studies
- Cabrera, C., et al. (2022). MAACO: A Dynamic Service Placement Model for Smart Cities
- Cabrera, C., et al. (2023). Machine Learning Systems: A survey from a Data-Oriented Perspective
- Cabrera, C., et al. (2025). The Systems Engineering approach in times of Large Language Models
Web
- Deploying Machine Learning using Flask
- MLOps: Continuous delivery and automation pipelines in machine learning
- Kubeflow: Machine Learning Toolkit for Kubernetes
- MLflow: An open source platform for the machine learning lifecycle
- TensorFlow Serving
- TorchServe: Model serving for PyTorch
- Seldon Core: Cloud native machine learning deployment
- Weights & Biases: MLOps platform
- Neptune.ai: Experiment tracking and model registry