Merci d'avoir envoyé votre demande ! Un membre de notre équipe vous contactera sous peu.
Merci d'avoir envoyé votre réservation ! Un membre de notre équipe vous contactera sous peu.
Plan du cours
Introduction and Team Use Case Selection
- Overview of AI in industrial environments
- Use case categories: quality, maintenance, energy, logistics
- Team formation and scoping of project objectives
Understanding and Preparing Industrial Data
- Types of industrial data: time-series, tabular, image, text
- Data acquisition, cleaning, and preprocessing
- Exploratory data analysis with Pandas and Matplotlib
Model Selection and Prototyping
- Choosing between regression, classification, clustering, or anomaly detection
- Training and evaluating models with Scikit-learn
- Using TensorFlow or PyTorch for advanced modeling
Visualizing and Interpreting Results
- Creating intuitive dashboards or reports
- Interpreting performance metrics (accuracy, precision, recall)
- Documenting assumptions and limitations
Deployment Simulation and Feedback
- Simulating edge/cloud deployment scenarios
- Collecting feedback and improving models
- Strategies for integration with operations
Capstone Project Development
- Finalizing and testing team prototypes
- Peer review and collaborative debugging
- Preparing project presentation and technical summary
Team Presentations and Wrap-Up
- Presenting AI solution concepts and outcomes
- Group reflection and lessons learned
- Roadmap for scaling use cases within the organization
Summary and Next Steps
Pré requis
- An understanding of manufacturing or industrial processes
- Experience with Python and basic machine learning
- Ability to work with structured and unstructured data
Audience
- Cross-functional teams
- Engineers
- Data scientists
- IT professionals
21 Heures
