Time Series Analysis (TSA) and Deep Learning

Time series data records quantities that represent or trace the values taken by, a variable over a period such as a month, quarter, or year. In other words, time series data describes something over time. We are surrounded by time series data. What makes time series data so important is that it allows one to see not only a single quantity in isolation, but at the same time, it gives us the typical “context” for the measured amount.

Other white papers in this series have described advances in Graphics Processing Units (GPU)-accelerated deep learning. This paper builds upon that topic and highlights time series analysis with deep learning’s neural networks. The paper will also highlight Technica’s FUNL product, a GPU-accelerated graph analytics engine, which is in the process of implementing time series analysis with
deep learning.