Deep Learning & Neural Networks w/ Python, Pandas, Keras, & TensorFlow («H36445»)

• Gaining in-depth knowledge of the concepts and methods of deep learning
• Learning about the possibilities and limitations of the technology
• Creating, training, and optimizing your own data models and neural networks
• Becoming familiar with the practical use of the most important Python frameworks and their application in your own projects
• Acquiring in-depth theoretical knowledge of deep learning and gaining practical experience in the application of modern AI technologies
• Evaluating, adapting, and productively applying neural networks
• Learning how to use the technologies in your own projects

1 Introduction to Deep Learning

• What are neural networks and how do they learn?
• Mathematical fundamentals explained concisely
• Neural networks with Keras and TensorFlow
• Models: evaluation and adaptation
• Models: use and storage

2 Data preparation and feature extraction

• Data preparation with Pandas
• Exploratory data analysis
• Standardization of numerical data and text data
• Feature extraction: extracting features from data
• Training networks with small amounts of data

3 Specialized neural networks

• Convolutional neural networks (CNN)
• Updating weights in CNNs
• Max pooling and dropout
• Monitoring training processes with TensorBoard
• Recurrent neural networks (RNN)
• Time series analysis and text processing with RNN

4 Deploying models and transfer learning

• Using cloud GPUs for machine learning projects
• Introduction to transfer learning and Model Zoo
• Introduction to ImageNet, ResNet, VGG16
• Using pre-trained layers in your own projects

This online seminar will be held in a group of no more than 12 participants using Zoom video conferencing software. Individual support from the instructors is guaranteed.

The exercises will be provided in the form of Jupyter Notebooks, which you can install locally on your own computer. The computationally intensive training of the data models will be performed on freely available cloud GPUs.

The instructors will be available to assist you with the practical exercises – in the virtual classroom or individually in breakout sessions.

After registering, you will find all the information, downloads, and extra services related to this qualification measure in your online learning environment.

This training is aimed at anyone who wants to understand machine learning in detail and use it in their own projects. This course is a valuable building block in the qualification process to become a data scientist, data engineer, and machine learning engineer.

Basic knowledge of programming with Python is required. Further technical, mathematical, and statistical knowledge is helpful but not required.

We recommend booking at least 14 days before the seminar date so that you can receive any documents by post in good time.