The master module Advanced Data Analytics for Management Support (ADAMS) is offered at the Humboldt-University of Berlin by the Chair of Information Systems.
ADAMS introduces students to recent developments in the scope of data-driven decision support. It focuses on deep learning and its applications in business and society. Special emphasis is given to the analysis of textual data and other complex data such as sequences and images.
Topics covered in the module include but are not limited to:
- Fundamentals of artificial neural networks
- Fundamentals of natural language processing (NLP)
- Neural word embeddings: word2vec and cousins
- Recurrent networks for sequential data processing
- Methodological principles of RNNs
- RNN applications in finance and language modeling
- Text classification and sentiment analysis
- Convolutional neural networks for image and text analysis
- NLP transfer learning
- Attention and transformers
The repository provides Jupyter notebooks that revisit concepts covered in the lecture and demonstrate their application using Python. Corresponding notebooks are available in the folder demos.
Anoter folder called exercises provides another set of Jupyter notebooks, which task students to practice their Python and Deep Learning skills on programming exercises. The exercises related to the lecture chapter and the demo notebooks. The idea of the exercises is that students try to solve the programming tasks themselves or with peers in their study group. Further, weekly tutorial sessions offer an opportunity to ask questions and discuss the exercise tasks with your lecturer. More detailed information on the coures format, organization, and logistics is available on the ADAMS Moodle page. That page also provides slides for lecture sessions and video recordings.