Modeling Machine Learning: A Cognitive Economic Approach
Andrew Caplin, Daniel Francis Martin, Philip Marx · National Bureau of Economic Research · 2022
What do machines learn, and why?To answer these questions we import models of human cognition into machine learning.We propose two ways of modeling machine learners based on this join: feasibility-based and cost-based machine learning.We evaluate and estimate our models using a deep learning convolutional neural network that predicts pneumonia from chest X-rays.We find these predictions are consistent with our model of cost-based machine learning, and we recover the algorithm's implied costs of learning.