Description
A working introduction to machine learning for people with engineering data rather than a data science background. Condensed public version of our multi-day bespoke course, focused on the models that actually earn their keep on sensor data.
What you will leave with
- Frame an engineering problem as a tractable ML problem
- Build anomaly detection that survives contact with noisy real data
- Produce a short-horizon forecast and know how far to trust it
- Deploy a small model to the edge and understand the constraints
Agenda
| Framing: which problems are worth a model at all | |
| Preparing engineering data — gaps, drift, resampling, labels | |
| Anomaly detection on real sensor traces | |
| Forecasting and prediction horizons | |
| Validation that does not lie to you | |
| Edge deployment: size, latency and power budgets |
Who it is for
Engineers who own equipment or process data and want to use it predictively.
Prerequisites
Basic Python. No prior ML experience assumed.
Format
- Duration: Full day (09:00–17:00)
- Level: Intermediate
- Group size: maximum 10 attendees
- Delivery: live online, or in person by arrangement
Need this for a whole team, or extended to full length on your own systems? We deliver every workshop as a bespoke on-site course too — talk to us.
Reviews
There are no reviews yet.