Understanding Deep Learning: Develop Neural Networks in Python
If you want to support me: When you purchase the course through my link here, I receive a higher sales commission from Udemy than if the course is accessed and purchased through the platform directly.
Udemy assures me that you will receive the current best price at which this course is currently sold on the Udemy marketplace. So you should not pay more through my link than if you buy the course directly through the platform.
Neural networks form a sub-area of machine learning, which describes the approach to realize artificial intelligence (AI) using statistical methods. The structure of artificial neural networks is inspired by the functioning of biological neurons and allows learning general patterns from special data. Rules derived from this can then be applied to new data, for example to make predictions.
The goal of this course is to give participants a deep understanding of neural networks: after completing the course, participants have not only understood statistical methods such as logistic or linear regression and parameter formation for models of neural networks, but can also flexibly apply their knowledge to advanced problems in interdisciplinary contexts.
After this course, participants will:
- Know the complete range of applications and the power
- Understand how neural networks can make predictions
- Have understood the learning mechanism of neural networks
- Know the relationship of (hyper-)parameters with the learning mechanism of a network and how these parameters are optimally set
- Increase the accuracy of a model by additionally generating data
The theory, presented clearly and in detail, is consistently supported by practical examples to make the techniques comprehensible for participants and to sharpen their (statistical) intuitions.