Stop overkilling simple tasks with black-box models and use transparent models instead
This addresses the problem of model overkill for practitioners and researchers, but it is incremental as it reiterates existing calls for model transparency without new empirical results.
The paper argues that deep learning models are overused for simple tasks where they are not necessary, and advocates for using transparent models instead to avoid unnecessary complexity.
In recent years, the employment of deep learning methods has led to several significant breakthroughs in artificial intelligence. Different from traditional machine learning models, deep learning-based approaches are able to extract features autonomously from raw data. This allows for bypassing the feature engineering process, which is generally considered to be both error-prone and tedious. Moreover, deep learning strategies often outperform traditional models in terms of accuracy.