Data Analysis & Machine Learning
e-learning, stats
Duration 50 Hours
1330 excluding VAT / person
E-Learning has a high drop-out rate, so why do our courses have a success rate of 90 %? The key? Our content! No handouts to put you to sleep.
Kayla is a Green Belt at the B&B factory in Baumé, and is facing some real problems. We need to help her find solutions.
Still need support? We offer tutoring sessions with our Master Black Belts trainers to support you!
Solving industrial problems
The Data Analysis & Machine Learning course is lively and interactive. The resources provided will enable you to master the subject perfectly.
Programme
Understanding the scope of Machine Learning and data analysis
- Understanding the objectives of Machine Learning
- Put Machine Learning in the context of Big Data, Artificial Intelligence...
- Know how to map the different tools: regression, dimension reduction, clustering, supervised (S) and unsupervised (NS) classification.
- Understanding what can and cannot be done with Machine Learning
Preparing data for proper analysis
- Preparing a data collection plan
- How to draw up a sampling plan
- Know how to apply the principles of descriptive statistics to data (type of distribution, calculation of mean statistics, median standard deviation, kurtosis, skewness, etc.).
- Assessing the presence of outliers
Knowledge of the principle: dimension reduction tools (NS)
- Know the principle of dimension reduction
- Understanding and using ACP, UMAP and TSNE tools
- Principal component analysis
- Correspondence factor analysis
- Multiple correspondence analysis
- Understanding and using a T2 card
Unsupervised classification
- Knowledge of the principle: unsupervised classification (NS) tools
- Hierarchical classification: Dendrogram, Variables, Individuals
- Know the principles of the K means, DBSCAN and Mean Shift algorithms
Supervised learning, continuous Y
- Know the principle and know how to use the tools: linear regression, multiple linear regression
- Understand the principle of neural networks and know how to apply them to simple cases
Supervised learning, discrete Y
- Logistic regression
- Ordinal logistic regression
- Supervised classification SVM
- KNN and decision tree
Metric of a classifier
- ROC curve and confusion control
- Simple classifier metrics
- Combined metric
- Confidence interval for metrics
Putting Machine Learning tools into practice
- Mastering the use of the Ellistat Data Analysis module to implement all the points in the programme
Objectives
- Familiarity with the principles and use of Data Analysis and Machine Learning tools in an industrial context.
- The training is based on the tools available in the Ellistat Data Analysis module.
For whom
This e-learning course is designed for managers and engineers who need to analyse production data in order to gain a new understanding or develop a predictive model of behaviour.
Prerequisites
- Basic use of the Internet and a web browser
- A level II qualification and/or 5 years' initial professional experience
- A basic understanding of quality and process management
- You do not need to be a Six Sigma Green Belt or Six Sigma Black Belt to take this course.
Duration
50 hours of lessons and exercises. E-Learning is available 24/7 for 3 months for this course.
Access times
Entries are permanent. So you can start this course at any time!
Accessibility
This training course is accessible to people with disabilities. Please contact us for details of special arrangements. We will do our utmost to accommodate you.
Solving industrial problems
The Data Analysis & Machine Learning course is lively and interactive. The resources provided will enable you to master the subject perfectly.
Your feedback
Previous
Next
