- akce již proběhla.
Seminar – MATLAB: Current trends in Engineering Education & Demystifying deep learning
26. března @ 8:30 - 13:00
Current trends in Engineering Education
Alessandro Tarchini (MathWorks)
Universities around the world are revamping curriculum to cover areas like „new machines“ based on the acknowledgement that traditional systems within industries are now extending to include more and that disciplinary boundaries have blurred.
Facing industry driven mega-trends like electrical activation, inter-system communication or data science and AI, universities have to adapt content and format to the increasing demand for cross-disciplinary approach to problem-solving.
Engineering software tools have become an essential part of „treating engineering students like engineers“ not only because as they graduate and integrate into the workforce they must be familiar with these techniques, but also because they help universities to deal with issues like attractiveness of engineering education, retention and employability of students.
Let’s have a look at how some of the most innovative engineering universities in the world are integrating engineering software tools in their curriculum.
Demystifying deep learning: A practical approach in MATLAB
Loren Shure (MathWorks)
Deep learning, a chief driver of the AI revolution, can achieve state-of-the-art accuracy in many cognitive or perceptual tasks such as naming objects in a scene or recognizing optimal paths in an environment.
It involves assembling large data sets, creating a neural network, and training, visualizing, and evaluating different models, using specialized hardware – often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.
In this seminar, we’ll demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. We’ll build and train neural networks that recognize handwriting, categorize foods, classify signals, and control machines.
Topics within this talk include the following:
- Manage large data sets (images, signals, text, etc.)
- Create, analyze, and visualize networks, and gain insight into the black box nature of deep learning models
- Automatically label ground truth or generate synthetic data
- Build or edit deep learning models with a drag-and-drop interface
- Perform classification, regression, and semantic segmentation with images or signals
- Apply reinforcement learning with deep Q networks (DQN)
- Leverage pre-trained models (e.g. GoogLeNet and ResNet) for transfer learning
- Import models from Keras-TensorFlow, Caffe, and the ONNX Model format
- Speed up network training with parallel computing on a cluster
- 8:30 – Registrace
- 9:00 – Current trends in Engineering Education
- 9:30 – Demystifying deep learning: A practical approach in MATLAB – 1. část
- 10:30 – Přestávka
- 11:00 – Demystifying deep learning: A practical approach in MATLAB – 2. část
- 12:00 – Diskuse a závěr