Next in JEL:
Deep learning provides powerful ways to extract structured information from large-scale, unstructured and graphical data sets. For example, economists may wish to detect the presence of economic activity in satellite images, or measure topics or businesses mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, including methods such as classifiers, regression models, generative AI, and embedding models. Applications include classification, document digitization, record linking, and data analysis methods for large-scale text and image organization. If the right methods are used, deep learning models can be cheap to tune and can scale to problems involving millions or billions of data points. The review is accompanied by a regularly updated companion website, EconDL, with easy-to-use demo manuals, software resources, and a knowledge base that provides technical information and additional applications.
Written by Melissa Dell. And here is my previous CWT with Melissa Dell.
Source link