I haven’t written anything here in so long, it seemed too daunting to get back into something technical. Instead, I will state a problem and some resources to help you solve that problem. The problem: there are many methods for analyzing time series — and some use deep learning, and others do not. If you’re interested in deep learning methods, and are worried keeping up with the proliferation of architectures and methods, here are some resources might help — they offer summaries, explanations, and surveys, and both are fairly recent, so you should be if not au courant with the SOTA, then at least able to fake it at a cocktail party.

# Deep Learning in Time Series Analysis

This is a book by Arash Gharehbaghi, and was published in ** July 2023.** Here’s some of the description:

Deep learning is an important element of artificial intelligence, especially in applications such as image classification in which various architectures of neural network, e.g., convolutional neural networks, have yielded reliable results. This book introduces deep learning for time series analysis, particularly for cyclic time series. It elaborates on the methods employed for time series analysis at the deep level of their architectures. Cyclic time series usually have special traits that can be employed for…