Deep neural networks are becoming irreplaceable for analyzing most kinds of data that humans supposed to exceed in - images, video, sounds, texts. They can not only predict something based on some input but also generate new images or sounds. Meanwhile, we are forgetting about another very important source of data - signals (or time series, which will be interchangeably here), that gets less hype in public but benefits a lot from applying deep learning comparing to classical approaches.
In this talk, we will review what are sources of time series and what business goals are we solving while analyzing them, what are “old” tools for analysis and how deep neural nets overcome them, we will learn the latest trends and ruin some myths and, moreover, we will see how generative models can be applied to the signal processing as well.
After this talk, you’ll be able to boost your current solutions in signal processing or time series analysis with deep learning. It will be also interesting for practitioners in other areas, like computer vision or NLP since we will discuss some concepts that are widely applicable. Previous experience with time series is not required, but some theoretical or practical experience with machine learning and/or neural networks is preferred.
Feedback form: https://python.it/feedback-1716
in __on Friday 3 May at 18:00 **See schedule**