Holistic applied AI in engineering – Deep learning for sequential process data
This application-oriented course on deep learning for sequential process data is particularly aimed at those interested in the field of engineering. Sequential process data are understood to be time series data from the industrial sector. For this type of data, the necessary foundational knowledge and practical skills for your own application are taught through a mixture of theoretical fundamentals and application-oriented examples.
Overview
The course "Deep Learning for Sequential Process Data" offers a practice-oriented introduction to the field of recurrent neural networks with TensorFlow, with a particular focus on engineering. Both sensors and machines often provide data in the form of time series. Therefore, this online course imparts knowledge on special deep learning approaches and their application based on TensorFlow, using learning videos, practical examples, self-assessment tests and hands-on exercises.
What content can I expect?
- Insight into deep learning methods with a focus on time series data and recurrent neural networks
- Application of recurrent deep learning methods using TensorFlow
What will I achieve?
Upon completion of the course, you will be able to...
- explain the difference between machine learning and deep learning.
- describe the elements and characteristics of recurrent neural networks.
- use various layer concepts (RNN, LSTM, Dense, Dropout) to build and apply a neural network in TensorFlow.
What requirements do I need?
- Prior knowledge in engineering
- Basic knowledge of engineering mathematics
- Fundamentals in the field of machine learning, e.g. from the “Machine Learning in Production” course
- Basic programming knowledge is an advantage but not necessary
