Personalization of Deep Learning
This work addresses the challenge of tailoring AI models to individual users, though it appears incremental as it builds on existing personalization concepts.
The paper tackles the problem of personalizing deep learning models for individuals by exploring curriculum learning and data grouping techniques, showing that these methods improve performance on individual data but often reduce performance on broader datasets.
We discuss training techniques, objectives and metrics toward personalization of deep learning models. In machine learning, personalization addresses the goal of a trained model to target a particular individual by optimizing one or more performance metrics, while conforming to certain constraints. To personalize, we investigate three methods of ``curriculum learning`` and two approaches for data grouping, i.e., augmenting the data of an individual by adding similar data identified with an auto-encoder. We show that both ``curriculuum learning'' and ``personalized'' data augmentation lead to improved performance on data of an individual. Mostly, this comes at the cost of reduced performance on a more general, broader dataset.