Deep Learning for Engineers
This video series addresses deep learning topics from the perspective of solving practical engineering problems. Learn how to apply specific deep learning techniques needed to successfully deploy your deep learning model, including:
- Accessing the right data
- Preprocessing your data to make it useful
- Using transfer learning to develop a network
- Deploying your model into a larger design
This video introduces deep learning from the perspective of solving engineering problems. Learn what it is, what it’s well-suited for, and why it can work when traditional methods fall short.
This video covers the first step in deep learning: ensuring you have data to train the network. Learn if deep learning is right for your project based on the type and amount of data you have for training.
Data Preprocessing and the Short-Time Fourier Transform
Data in its raw form may not be ideal for training a network. Discover how to preprocess data to make training faster and simpler, and to ensure that it converges on a solution.
This video uses a transfer learning example that shows you how to develop a network that can recognize high five motions in acceleration data.
Deploying Deep Learning Models
This video covers the additional steps needed once you have a deep neural network: incorporating it into a larger design, gaining confidence in the system, and deploying it onto a target device.
