Deep Learning as a Projection Method for Solving Economic Models -- by Kenneth L. Judd, Karl Schmedders
EconomicsData Science
THE AI ANGLE
Serving as an adaptive projection tool for solving economic modelsEconomists Kenneth Judd and Karl Schmedders classified neural-network solvers as least-squares projection methods with adaptive nonlinear parameterizations. Their paper reframes deep learning as an addition to classical numerical methods rather than an entirely separate framework. This places neural networks alongside linear-basis and sparse-grid methods within a single modeling toolkit.
THE TEACHING ANGLE
Students can examine whether trained neural networks offer real computational advantages over simpler linear-basis methods in low and moderate dimensions.Read the original at nber.org Generate teaching or study materials
More in Economics
- We need ‘right to intervene’ in AI amid growing threat, says Bank of England bossThe Guardian — Technology · September 30, 2026
- Fearing AI, young workers retrain for hands-on jobsThe Hechinger Report · September 30, 2026
- The Macroeconomic Effect of AI: Sizing the Software Engineering Channel -- by Alex Blumenfeld, Jonathon Hazell, Chen Lian, Andreas SchaabNBER Working Papers · September 29, 2026
- AI has made borrowing more expensive – an expert explains how bond markets are changingThe Conversation — AI · September 29, 2026