Deep Learning and Advanced AI Techniques (CE-AI)
Deep Learning and Advanced AI Techniques (CE-AI)
Modulleitung
Studiengänge
Masterstudiengang Wirtschaftsinformatik (MSc WI)
(01.09.2019)
Inhalt
Deep Learning and Advanced AI Techniques cover the basics of deep learning and advanced AI techniques and recent technological trends. It also includes a few aspects of generative AI. The course covers:
• Fundamentals of artificial intelligence
• Reinforcement learning – Learning to play games and beyond
• Fundamentals of deep learning, network design, and training
• Transfer learning and pre-trained models
• Data augmentation and synthesis
• Core ideas of: Graph Neural Networks, Autoencoders, Generative adversarial networks (GANs), recurrent neural networks, convolutional neural networks, diffusion models
• Explainability and interpretability in AI
• Case studies and applications in various industries and for various tasks
• Recent trends and future directions in AI and deep learning
• Fundamentals of artificial intelligence
• Reinforcement learning – Learning to play games and beyond
• Fundamentals of deep learning, network design, and training
• Transfer learning and pre-trained models
• Data augmentation and synthesis
• Core ideas of: Graph Neural Networks, Autoencoders, Generative adversarial networks (GANs), recurrent neural networks, convolutional neural networks, diffusion models
• Explainability and interpretability in AI
• Case studies and applications in various industries and for various tasks
• Recent trends and future directions in AI and deep learning
Lehrmethode
• The course involves interactive lectures with exercises to integrate theoretical knowledge with practical design and analysis skills.
Lernergebnisse
After successful completion of the course, students will
Professional competence
• understand the basic concepts and methods of artificial intelligence and deep learning
• be able to identify suitable applications for artificial intelligence and deep learning
• understand key concerns in adopting and leveraging artificial intelligence
Methodological competence
• select, use, and adjust existing models and methods for a given task or data set
Personal competence
• critically reflect on analytical outcomes
• be able to improve and mitigate self-inflicted errors
Technological competence
•be able to use a deep learning framework such as Keras
Professional competence
• understand the basic concepts and methods of artificial intelligence and deep learning
• be able to identify suitable applications for artificial intelligence and deep learning
• understand key concerns in adopting and leveraging artificial intelligence
Methodological competence
• select, use, and adjust existing models and methods for a given task or data set
Personal competence
• critically reflect on analytical outcomes
• be able to improve and mitigate self-inflicted errors
Technological competence
•be able to use a deep learning framework such as Keras
Literatur
• Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Harlow, UK: Pearson.
• Bishop, C. M. (2024). Deep Learning Foundations and Concepts. Springer.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. Cambridge, MA: The MIT Press.
• Bishop, C. M. (2024). Deep Learning Foundations and Concepts. Springer.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. Cambridge, MA: The MIT Press.
Prüfungsmodalitäten
Written exam