The topic: the promises and pitfalls of Artificial Intelligence (AI) and Machine Learning (ML). A wide ranging discussion with plenty of questions from the audience. Subjects covered included:
- Use of AI vs ML
- Approaches to your project
- Use for Predictive Maintenance, Production or Quality Optimisation
The panel discussed AI vs ML and the differences between them. The vast majority of current projects are currently ML – which is very suited to highly repetitive processes such as manufacturing.
We are now starting to see more AI projects, especially for process optimisation, but these are still outnumbered by the use of ML.
Some notable points:
- >50% of current AI/ML projects in industry are already delivering value
- Ensure you understand the question you are trying to answer, then validate your approach and finally make sure you understand the outcomes required
- Ensure you have appropriate data available
- For Machine Learning make sure you have data to describe failures to train the algorithms
- Expect to spend at least 2/3rds of your time sorting out your data!
To see the full video: AI / #ML the Promise and the Pitfalls | #PIWorld #PI