Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning for Economists

Melissa Dell

TL;DR

This review introduces deep neural networks, covering methods such as classifiers, regression models, generative artificial intelligence (AI), and embedding models, covering applications including classification, document digitization, record linkage, and methods for data exploration in massive-scale text and image corpora.

Abstract

Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images, or to measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative AI, and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points.. The review is accompanied by a companion website, EconDL, with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications.

Deep Learning for Economists

TL;DR

This review introduces deep neural networks, covering methods such as classifiers, regression models, generative artificial intelligence (AI), and embedding models, covering applications including classification, document digitization, record linkage, and methods for data exploration in massive-scale text and image corpora.

Abstract

Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images, or to measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative AI, and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points.. The review is accompanied by a companion website, EconDL, with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications.
Paper Structure (32 sections, 6 equations, 14 figures, 4 tables)

This paper contains 32 sections, 6 equations, 14 figures, 4 tables.

Table of Contents

  1. Introduction
  2. An Overview of Deep Learning
  3. What is deep learning?
  4. Foundational Deep Learning Architectures
  5. The Basics of Neural Networks
  6. Convolutional Neural Networks
  7. Recurrent Neural Networks
  8. The Transformer
  9. Transformer Large Language Models
  10. Vision and Audio Transformers
  11. Optimizing Neural Networks
  12. Training Data
  13. Bias and Uncertainty Quantification
  14. Reusability and Reproducibility in Deep Learning
  15. Classifiers
  16. ...and 17 more sections

Figures (14)

  • Figure 1: Flowchart for approaching classification.
  • Figure 2: Classifying text.
  • Figure 3: Tasks performed with a transformer encoder language model.
  • Figure 4: Share of newswire articles with a given binary topic tag.
  • Figure 5: Shares of entity types in newswire articles.
  • ...and 9 more figures