Fundamentals and Applications of Machine Learning
From core methods to practical applications in business.
The Machine Learning / Deep Learning module enables participants to confidently distinguish between different areas of machine learning, identify suitable use cases within their own work environment, and develop, train and compare their first ML and DL models using meaningful performance metrics. The course follows an interactive approach, progressing from classical machine learning and neural networks to image processing with deep learning – from fundamental concepts to well-founded model selection.
All practical exercises are carried out directly in Jupyter Notebooks using real-world, industry-related datasets, allowing participants not only to understand the complete ML workflow but also to work through it themselves. Rather than focusing solely on the use of tools, the course emphasizes the transition from user to solution designer: translating business requirements into data-driven solutions and realistically assessing their quality and limitations.
The course concludes with a practical application to the participants’ own organizations, including the independent identification and evaluation of potential machine learning use cases.
Course Structure
Dauer: 0,5 – 2 Tage
Day 1 – Classical Machine Learning
Block 1: Machine Learning Fundamentals
Block 2: Overview of Machine Learning Types
Block 3: Data Preprocessing
Block 4: Model Application and Evaluation Metrics
Day 2 – Deep Learning & Practical Application
Block 5: Introduction to Neural Networks and Deep Learning
Block 6: Deep Learning for Image Processing
Block 7: Practical Application: Case Study
Block 8: Practical Exercise & Conclusion
The course content can be flexibly adapted to the participants’ prior knowledge, industry background and objectives.
Keywords
Machine Learning, Deep Learning, Artificial Intelligence, AI Training, Machine Learning Fundamentals, Supervised Learning, Unsupervised Learning, Classification, Regression, Clustering, Anomaly Detection, Feature Engineering, Data Preprocessing, Data Cleaning, Encoding, One-Hot Encoding, Feature Scaling, Train-Test Split, Data Leakage, scikit-learn, Python, Jupyter Notebook, Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbors, Model Evaluation, Accuracy, Precision, Recall, F1-Score, Confusion Matrix, ROC-AUC, Neural Networks, CNN, Convolutional Neural Network, RNN, LSTM, Transformer, Backpropagation, Overfitting, Transfer Learning, MobileNetV2, Data Augmentation, Image Classification, Computer Vision, Grad-CAM, Explainable AI, Predictive Maintenance, Quality Control, Data Science Life Cycle, MLOps, LLM, n8n, AI Use Case, Industrial AI, AI in Manufacturing