Introduction to AI in the High Tech Manufacturing Industry

Duration 5 weeks
Weekly workload 8 to 12 hours
Course dates 3, 10, 17 and 24 June and 1 July 2021
Tuition fee 2,950 VAT exempt
Location JADS Mariënburg / EAISI Gaslab / Online depending on Covid situation

Discover what AI in High Tech Manufacturing industry is really about in this 5-day program. 

The program combines a practical approach, working through example AI projects thereby showing how to successfully execute an AI project, with building a solid understanding of the fundamental principles underlying machine learning.

The teaching staff possesses a combination of scientific excellence and deep practical knowledge. Let them teach you about loading, exploring, and preparing data, about correlation and regression, supervised learning, nearest neighbor classification, linear classification, model complexity and decision boundaries, decision trees, random forests, support vector machines, under-fitting and overfitting, unsupervised learning, dimensionality reduction, principal components analysis, t-SNE, and much more.


What you will do

You learn about the different types of artificial intelligence projects and whether or not a certain type of project is suitable for a machine learning approach. By working through the example projects you learn to recognize and deal with typical challenges and common pitfalls. The example projects cover the phases of business understanding, data understanding, data preparation, modeling and evaluation of the CRISP-DM model. It also teaches you to critically think about what to achieve with an AI project, how to capture that in a performance metric and how to assess whether your models generate value to your organisation.

The course focuses on the principles of machine learning: what is it? How does it work? What can you do with machine learning? Why does machine learning have so much impact, and what are typical applications in high-tech? During the course, we discuss implementations of machine learning in Python. Learning to code in Python is not part of this course, nor is it required that you already know how to code.

The Program day 1 & 2

Day 1: Artificial Intelligence and AI Project Execution


  • AI, machine learning, data science. What are they? Why do they have so much impact?
  • What’s new? New forms of data, new analytics and new business opportunities.
  • Machine learning: how does it work? what can you do with it.
  • Machine-learning workflow: translating a goal to a machine-learning problem, and choosing the right technique.
  • Training an algorithm, and finetuning its complexity.
  • The CRISP-DM model for machine-learning projects.


  • Introduction to the case.
  • Describing and visualizing data
  • Descriptive analytics
  • Going from Data Understanding back to Business Understanding (CRISP-DM iteration)

Day 2: Data Preparation


  • Data Preparation
  • Feature selection and feature engineering


  • Selecting, cleaning and constructing data
  • Feature selection and feature engineering
  • Cross-validation

The Program day 3 till 5

Day 3: Modeling: Supervised Learning


  • Basic supervised learning algorithms
  • Regression and classification
  • Performance metrics, also in relation to business understanding
  • Evaluation / interpretation of results (does it meet business objectives)


  • Regression models (linear regression, LASSO, KNN)
  • Classification models (SVM, CART, Random Forests, Gradient Boosting)
  • Visualization and tuning
  • Describing results

Day 4: Modeling: Unsupervised Learning


  • Basic unsupervised learning algorithms
  • Clustering (k-means, hierarchical clustering)
  • Dimensionality reduction (PCA, t-SNE)


  • Hands-on exercises with clustering  and dimensionality reduction
  • Underfitting and overfitting

Day 5: Recap, reflection, and best practices


  • Recap of all theory covered in course and reflection on the role of AI in high-tech
  • Wrap-up
JADS Marienburg campus

Your profile

  • You want to learn what AI can mean for your career and organization;
  • You want to dive deep into a specific topic;
  • You work in a technical role and/or a managerial role;
  • You have  a BSc or MSc and at least 3 years of working experience.

You walk away with

After completing the 5-day program, participants:

  • Have an overview of the fields of Artificial Intelligence and Machine Learning;
  • Understand the type of problems one can solve with which type of AI techniques;
  • Can execute an AI project using the CRISP-DM methodology;
  • Understand the basic principles underlying commonly used AI techniques;

Teaching in Covid times …

We’ve created a welcoming and warm online teaching environment, which we use as long as the covid situation prevents classroom teaching. Instructors and teaching technologies are adjusted to online teaching. We miss the friendly and inspirational atmosphere of our historic campus, but the teaching effectiveness of online course matches that of classroom teaching!

Upcoming information session

Our professors

Dr. Jerry de Groot

Jerry is sr. data scientist at Holland Innovative. With a background in applied physics, he specialized in medical-device technology. Jerry learned data science and machine learning through his academic research in the Amsterdam Medical Center. He is keen on figuring out how things work (or don’t), loves prototyping and has a natural ability to explain complex abstractions in plain language.

Prof. Jeroen de Mast

Jeroen is professor of statistics and data science at the University of Waterloo (Canada), Scientific Director at Holland Innovative, and Academic Director of Professional Education at JADS. Throughout his career, he has combined his academic positions with a career as consultant and professional trainer in industrial and systems engineering. Jeroen is an original and scholarly thinker, and an inspirational speaker, with a talent for explaining the essence of matters with much clarity.

Any questions? Get in touch.

Application form

  • Date Format: MM slash DD slash YYYY
  • This field is for validation purposes and should be left unchanged.
Group 5
Group 6
Group 7