Expectations for signal processing applications are getting higher. Engineers need to create applications that can intelligently respond to inputs or make predictions; often, this means incorporating AI systems into their designs.

What does every AI-powered signal processing application need? A lot of representative signal data, a good network architecture (because signal data works particularly well with deep learning), and the right signal processing tools to turn that data into a source for automated learning.

This ebook covers:

• The basics of deep learning for signal processing
• Using data sets and labeling to train and validate models
• Applying data augmentation and synthesis to improve the quality and quantity of training data
• Creating inputs for deep networks