Introduction

In this chapter, we will focus on data that is less static but streaming. Specifically, it is data where the temporal element plays a crucial role in the distribution of the data, such as speech and video. When processing such data, the distribution of the input data can often change rapidly over time. For example, in sensor data, we can have small peaks during rush hour and there can be a lot of changes in a video of a sports game. Another challenge with types of data is the size of the dataset for training. The datasets used for video classification are often larger than 100 GB. This means computing power is essential.