Rationally Inattentive Utility Maximization for Interpretable Deep Image Classification
This work provides a new economic-based interpretation for the behavior of deep CNNs, which could benefit researchers seeking to understand and predict model performance without extensive retraining.
This paper demonstrates that deep CNNs for image classification behave equivalently to rationally inattentive utility maximizers, a generative model from economics. Their interpretable model can predict the classification performance of deep CNNs with over 94% accuracy, eliminating the need for retraining.
Are deep convolutional neural networks (CNNs) for image classification explainable by utility maximization with information acquisition costs? We demonstrate that deep CNNs behave equivalently (in terms of necessary and sufficient conditions) to rationally inattentive utility maximizers, a generative model used extensively in economics for human decision making. Our claim is based by extensive experiments on 200 deep CNNs from 5 popular architectures. The parameters of our interpretable model are computed efficiently via convex feasibility algorithms. As an application, we show that our economics-based interpretable model can predict the classification performance of deep CNNs trained with arbitrary parameters with accuracy exceeding 94% . This eliminates the need to re-train the deep CNNs for image classification. The theoretical foundation of our approach lies in Bayesian revealed preference studied in micro-economics. All our results are on GitHub and completely reproducible.