Höchstleistungsrechenzentrum Stuttgart: Supercomputing-Academy: Natural Language Processing

Prerequisites and content levels

Prerequisites

Strong experience in Python programming.
Fundamental understanding of machine learning and deep learning techniques.
Basic familiarity with Linux.

Content levels

Intermediate: 30 hours

Learn more about course curricula and content levels.

Target audience

This course is intended for, but is not limited to, the following groups:

Postgraduate students from non-computer science backgrounds (e.g., engineers).
Research and business professionals working with text data.
Anyone interested in Natural Language Processing (NLP).

Course Objectives

Introduce key terminology and algorithms used in NLP.
Teach techniques for data preprocessing, cleaning, and preparation.
Offer hands-on experience in building NLP models with Python.
Explore various methods and tools for interpreting and visualizing model outputs.
Deepen understanding of different models and algorithms through practical tasks and quizzes.

Learning outcomes

After completing this course, participants will:

Exhibit a fundamental understanding of NLP terminology and techniques.
Apply NLP techniques and algorithms discussed throughout the course.
Implement data preprocessing, cleaning, and preparation methods for NLP applications.
Build and assess NLP models using Python.
Utilize various methods and tools to effectively interpret and visualize model outputs.

Instructor

Layal Ali (HLRS) layal.ali(at)hlrs.de

Agenda

Week 1: Introduction, Word Vectorization Techniques, Term Frequency- Inverse Document Frequency (TF-IDF), Named Entity Recognition (NER).
Week 2: Semantic Search, Topic Modeling, Sentiment Analysis, Text Summarization, Chatbots.
Week 3: Next Word Prediction, Transformers, Fine-Tuning LLMs, Retrieval Augmented Generation (RAG), LLM Distillation Techniques.

Registration information

Register via the button at the top of this page.
We encourage you to register to the waiting list if the course is full. Places might become available.

Registration closes on May 23, 2025.

Fees

40 Euro: Students without master’s degree or equivalent
90 Euro: PhD students or employees at a German university or public research institute
180 Euro: PhD students or employees at a university or public research institute in an EU, EU-associated or PRACE country other than Germany
360 Euro: PhD students or employees at a university or public research institute outside of EU, EU-associated or PRACE countries
960 Euro: Other participants, e.g., from industry, other public service providers, or government

Link to the EU and EU-associated (Horizon Europe), and PRACE countries.

HLRS concept for flexible learning

Flexible Learning

This course offers flexible learning, allowing you to learn at your own pace and access online course materials and cluster resources. Web-seminars are held weekly to discuss the learning modules and to answer your questions. We also provide forum channels that enable you to communicate with the lecturer and peers, as well as to share your experiences.

Learning Duration

The course is divided into multiple learning units of 10 hours each. Participants can learn the individual learning content on their own schedule. In addition, this course has fixed dates for virtual seminars and the exam.

Certificate & Attendance Confirmation

High-Performance Computing Center (HLRS) issues participants an attendance confirmation if they have attended all seminars, as well as a certificate if they have passed the exam at the end of the course.

Technical Requirement

Stable Internet connection so you can access and download the learning materials.
Access to video conferencing tool with camera and microphone for participation in regular seminars.

Contact

Layal Ali, phone 0711 685 60442, training(at)hlrs.de

HLRS Training Collaborations in HPC

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich. EuroCC@GCS is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC.

Further courses

See the training overview and the Supercomputing Academy pages.