|
Gaststudierendenverzeichnis >> Fakultät Humanwissenschaften >> Institut für Erziehungswissenschaft >>
|
Allgemeine Pädagogik
BA Pädagogik
Allgemeine Pädagogik - Basismodul III: Geschichte und Theorien der Erziehung und Bildung
MA Erziehungs- und Bildungswissenschaft
Vertiefungsmodul: Forschungsmethoden in der Erziehungs- und Bildungswissenschaft
|
EMP_MA_SE: Deep learning and artificial neural networks (Vertiefungsseminar quantitative Forschungsmethoden) [Vertiefungsseminar Quanti: Deep Learning] -
- Dozent/in:
- Matthias Borgstede
- Termine:
- Do, 12:00 - 14:00, MG2/01.11
- Inhalt:
- Artificial intelligence (AI) has made immense advances in recent years. Popular applications of AI such as text generation (chat bots), object recognition or autonomous driving are becoming more and more human-like. One of the most promising approaches in the field of AI are neural network models, especially deep learning frameworks.
This course gives a practical introduction to artificial neural networks and deep learning using the statistical programming environment R. Students will acquire the necessary skills to understand how modern AI works by constructing and training their own deep learning models. The course covers the theoretical background of neural networks, basic network architectures, as well as exemplary applications such as object classification, hand-written letter recognition or natural language processing.
The course language will be English.
- Empfohlene Literatur:
- Chollet, F., Kalinowski, T., Allaire, J.J. (2022). Deep learning with R. Manning.
Ciaburro, G., Venkateswaran, B. (2017). Neural networks with R. Packt.
Hodnett, M., Wiley, J.F. (2018). R Deep learning essentials. Packt.
The literature is freely available for students of Bamberg University via https://learning.oreilly.com
|
MA Erwachsenenbildung / Weiterbildung
Allgemeine Pädagogik - Basismodul III: Geschichte und Theorien der Erziehung und Bildung
Vertiefungsmodul: Forschungsmethoden in der Erziehungs- und Bildungswissenschaft
|
EMP_MA_SE: Deep learning and artificial neural networks (Vertiefungsseminar quantitative Forschungsmethoden) [Vertiefungsseminar Quanti: Deep Learning] -
- Dozent/in:
- Matthias Borgstede
- Termine:
- Do, 12:00 - 14:00, MG2/01.11
- Inhalt:
- Artificial intelligence (AI) has made immense advances in recent years. Popular applications of AI such as text generation (chat bots), object recognition or autonomous driving are becoming more and more human-like. One of the most promising approaches in the field of AI are neural network models, especially deep learning frameworks.
This course gives a practical introduction to artificial neural networks and deep learning using the statistical programming environment R. Students will acquire the necessary skills to understand how modern AI works by constructing and training their own deep learning models. The course covers the theoretical background of neural networks, basic network architectures, as well as exemplary applications such as object classification, hand-written letter recognition or natural language processing.
The course language will be English.
- Empfohlene Literatur:
- Chollet, F., Kalinowski, T., Allaire, J.J. (2022). Deep learning with R. Manning.
Ciaburro, G., Venkateswaran, B. (2017). Neural networks with R. Packt.
Hodnett, M., Wiley, J.F. (2018). R Deep learning essentials. Packt.
The literature is freely available for students of Bamberg University via https://learning.oreilly.com
|
|
|
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|