Dates & Booking

1. introduction to deep learning

• What are neural networks and how do they learn?
• Mathematical basics explained in compact form
• Neural networks with Keras and TensorFlow
• Models: evaluation and adaptation
• Models: use and storage

2. data preparation and feature extraction

• Data preparation with Pandas
• Exploratory data analysis
• Standardization of numerical data and text data
• Feature extraction: Extracting features from data
• Train networks with small amounts of data

3. specialized neural networks

• Convolutional neural networks (CNN)
• Updating weights for CNNs
• Max pooling and dropout
• Monitor teach-in processes with TensorBoard
• Recurrent neural networks (RNN)
• Time series analysis and text processing with RNN

4. deploy models and transfer learning

• Use of cloud GPUs for machine learning projects
• Introduction to transfer learning and the Zoo model
• Presentation of ImageNet, ResNet, VGG16
• Use pre-trained layers in your own projects

This training will provide you with in-depth knowledge of the concepts and methods of deep learning. You will learn about the possibilities and limitations of the technology and create, train and optimize your own data models and neural networks.

You will get to know the practical work of the most important Python frameworks and know how to use them in your own projects.

The technical hurdles for getting started are minimal - thanks to the use of Jupyter notebooks and free cloud GPUs.

After completing this training, you will not only have a sound theoretical knowledge of deep learning, but also gain practical experience in the application of modern AI technologies. You will be able to evaluate, adapt and productively use neural networks. You will also learn how to use the technologies in your own projects. This will qualify you for advanced tasks in AI development.

The content of this training supports the obligation to provide evidence of the promotion of AI competence within the meaning of Art. 4 EU AI Regulation.

This course offers you a digital blended concept that has been developed for part-time learning. Thanks to a flexible mix of online seminars and self-study phases, you are sure to reach your goal. This is how you learn in this course:

Learning environment: In your online learning environment, you will find useful information, downloads and extra services for this training course after you have registered.

Self-study phases: Learn independently, at your own pace and whenever you want. Our courses offer you didactically high-quality learning material. 

Live webinars: In regular online seminars, you will meet your trainers in person. You will receive answers to your questions, specific assistance and instructions on how to deepen your knowledge and apply the skills you have acquired in practical exercises.

Learning community: A digital learning community is available to you throughout the course. Exchange ideas with other participants and the trainers and ask questions.

Future Jobs Club: Get exclusive access to a business network, news and future work hacks.

Certificate of attendance and Open Badge: As a graduate of the course, you will receive a certificate of attendance and an Open Badge, which you can easily share in professional networks (e.g. LinkedIn).

You will learn what artificial intelligence is, how it works and what you can use AI for.

You will learn about the importance of data for automation, analysis and the creation of models and what is important when it comes to data quality .

You can clean and prepare data to implement your own mining or machine learning projects.

You will get to know the technical processes in machine learning and will be able to communicate these clearly within the company.

You will gain your first practical experience of working on data and training sets and will be able to apply your knowledge immediately afterwards.

You are able to make informed decisions about the use of AI in your company and can communicate with technical departments on an equal footing.

You will qualify in a new field of expertise that will play a major role in the future and is already in high demand today.

Take an active part in our online community and work with your own questions - this is how you will benefit most from this online training. This will allow you to apply the content both in self-study and in practical exercises.

1. python techniques for text processing

• Python basics for word processing
• Process text and PDF files
• The most important regular expressions

2. introduction to Natural Language Processing (NLP)

• Concepts of Natural Language Processing
• Use of the SpaCy library for text analysis
• Tokenization, stemming and lemmatization
• Part-of-speech and Named Entity Recognition
• Decomposition of texts with Sentence Segmentation

3. text classification and text analysis

• Introduction to scikit-learn
• Evaluation of classification models with precision, recall and F1 score
• Semantic understanding and sentiment analysis
• Vector-based text representations with Word Vectors
• Sentiment analysis with the NLTK library

4 Topic Modeling and Long Short-Term Memory

• Introduction to topic modeling
• Classification with Latent Dirichlet Allocation (LDA)
• Recognize structures with Non-negative Matrix Factorization (NMF)
• Long Short-Term Memory, GRU and Text Generation
• Implementation of an LSTM for text creation with Keras

5. transformer and attention

• The concept of self-awareness
• Multihead attention and meaning in NLP models
• Encoder and decoder for machine translation and language understanding
• Architectural concepts of common transformer models: GPT-2/3/4, BERT
• Creating a Transformer structure with Python and Keras
• Training and evaluation of a Seq2Seq transformer

6. transfer learning and fine-tuning with Hugging Face

• Introduction to Hugging Face and presentation of pre-trained models
• Selection of suitable models and tokenizers
• Transfer learning and fine-tuning of pre-trained models
• Automatic configuration and customization of models

7th practical project: Training your own chatbot

This training will provide you with in-depth knowledge of concepts and methods for using language-based artificial intelligence. You will get to know the basic technologies and acquire comprehensive knowledge of the transformer architecture, which is a key technology for modern generative AI.

You will learn the practical work with the most important Python frameworks and with pre-trained models on Hugging Face and know how to use them in your own projects.

The technical hurdles for getting started are minimal - thanks to the use of Jupyter notebooks and free cloud GPUs.

After completing this training course, you will not only have sound theoretical knowledge of language processing with artificial intelligence, but also practical experience in the application of methods and frameworks. You will be able to develop, adapt and productively use your own language systems and models based on machine learning. You will also learn how to use the technologies in your own projects. This will qualify you for advanced tasks in AI development.

The content of this training supports the obligation to provide evidence of the promotion of AI competence within the meaning of Art. 4 EU AI Regulation.

1. Introduction and basics

• Objectives, procedure, and alignment of expectations
• Value creation through generative AI in companies
• Classification of RAG in modern AI architectures
• Typical RAG use cases and limitations

2. Fundamentals of Retrieval-Augmented Generation

• Functionality and architecture of RAG systems
• Interplay between data, retrieval, and generation
• Common sources of error and quality issues
• Examples and best practices from real projects

3. Chunking and embeddings in practice

• Intuitive understanding of embeddings
• Chunking strategies and their effects
• Visualization of similarities in embedding space
• Hands-on implementation in Python notebooks

4. Retrieval, reranking, and generation

• Similarity Search and Top-K Retrieval
• Reranking strategies for better results
• Prompt design for RAG-based responses
• Implementation of a complete retrieval pipeline

5. Evaluation and optimization

• Why evaluating RAG systems is not trivial
• Quality metrics and automatic evaluation
• Systematic optimization of pipelines
• Comparison, parameter tuning, and traceability

6. Production deployment and MLOps

• Systematic optimization of RAG pipelines
• Parameter search, comparison, and traceability
• Experiment tracking & versioning (e.g., with MLflow)
• Implementation as a service with APIs and monitoring
• Deployment with FastAPI

7. Monitoring and drift

• Why RAG systems deteriorate over time
• Types of drift and their effects
• Practical drift analysis with modified data set
• Derivation of measures

In your online learning environment, you will find useful information, downloads and extra services for this training course once you have registered.

You will develop a deep, practical understanding of RAG-based AI systems and learn how they are technically structured.

You build complete end-to-end RAG pipelines yourself —from the data source to the productive API.

You will learn to critically evaluate RAG systems and systematically improve them, rather than just experimenting.

You understand how MLOps concepts are applied to LLM systems, including monitoring and drift analysis.

You will receive a practical blueprint that you can use to confidently transfer your own RAG solutions into the corporate context.

The prerequisite for taking the exam is participation in the four courses of the Master Class. We recommend attending all courses within a maximum of two years and completing the exam close to the last course attended.  

The content of all four Master Class courses is relevant for the exam.As soon as you have booked the exam, you will see it in your learning environment.There is a tile with more detailed information about the exam, as well as a small mini-preview of the format of the e-exam with various sample questions.  

The exam takes place online. It can be completed from the comfort of your own home or office within a set time frame. It consists of two parts: 

• E-exam: 20 multiple-choice questions on the content of the four Master Class courses. 
• Practical exam: Development of an ML use case with a specified data set. Depending on the preparatory work in the four Master Class courses, approximately 3–4 hours should be allocated for this task.