ML Basics for Manufacturing & Production Applications
Course Overview:
This course is designed to provide a comprehensive foundation in the fundamental concepts and techniques of AI learning, specifically tailored for applications in Production Control and Operations (P&OC). Participants will gain a deep understanding of the underlying principles and algorithms that power modern AI systems, and learn how to apply these concepts to solve real-world problems in production scheduling, capacity planning, inventory control, and workflow optimization.
Learning Objectives:
Understand the fundamental principles and techniques of AI learning and their relevance to Production Control and Operations
Apply supervised, unsupervised, and reinforcement learning algorithms to solve P&OC problems
Develop a strong intuition for model selection, hyperparameter tuning, and performance evaluation in the context of P&OC
Implement and deploy AI learning models using industry-standard tools and frameworks for production control and operations
Communicate the results and insights obtained from AI learning models to both technical and non-technical stakeholders in P&OC
Course Highlights:
1. Introduction to AI Learning in P&OC
Overview of AI learning and its applications in Production Control and Operations
Types of learning: supervised, unsupervised, and reinforcement learning
The AI learning process in P&OC: data preparation, model selection, training, evaluation, and deployment
Hands-on exercises: Setting up the development environment and working with P&OC datasets
2. Supervised Learning for P&OC
Overview of supervised learning and its applications in production control and operations
Algorithms for classification and regression (e.g., logistic regression, decision trees, support vector machines)
Model selection, hyperparameter tuning, and cross-validation techniques for P&OC problems
Hands-on exercises: Implementing supervised learning algorithms for production scheduling and quality control
3. Unsupervised Learning in P&OC
Overview of unsupervised learning and its applications in production control and operations
Algorithms for clustering, dimensionality reduction, and anomaly detection (e.g., k-means, PCA, autoencoders)
Techniques for data visualization and interpretation in P&OC
Hands-on exercises: Applying unsupervised learning algorithms for workflow optimization and anomaly detection in production processes
4. Reinforcement Learning for P&OC
Overview of reinforcement learning and its applications in production control and operations
Markov Decision Processes (MDPs) and the Bellman equation in the context of P&OC
Algorithms for value-based and policy-based reinforcement learning (e.g., Q-learning, SARSA, policy gradients)
Hands-on exercises: Implementing reinforcement learning algorithms for inventory control and capacity planning
5. Advanced Topics and Applications in P&OC
Deep learning architectures for AI learning in production control and operations (e.g., convolutional neural networks, recurrent neural networks)
Transfer learning and domain adaptation techniques for P&OC data
Real-world case studies and applications of AI learning in Production Control and Operations
Hands-on exercises: Developing an end-to-end AI learning pipeline for a P&OC problem
Prerequisites:
Strong understanding of mathematics, including linear algebra, calculus, and probability theory
Proficiency in programming with Python or R
Familiarity with basic machine learning concepts and algorithms
Knowledge of production control and operations management principles