Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …

This review highlights the efficacy of combining federated learning (FL) and transfer learning
(TL) for cancer detection via image analysis. By integrating these techniques, research has …

Transfer learning is beneficial by allowing the expressive features of models pretrained on
large-scale datasets to be finetuned for the target task of smaller, more domain-specific …

We study the problem of (learning) algorithm comparison, where the goal is to find
differences between models trained with two different learning algorithms. We begin by …

Data augmentation (DA) encodes invariance and provides implicit regularization critical to a
model's performance in image classification tasks. However, while DA improves average …

Pruning-that is, setting a significant subset of the parameters of a neural network to zero-is
one of the most popular methods of model compression. Yet, several recent works have …

Despite the impressive performance of current AI models reported across various tasks,
performance reports often do not include evaluations of how these models perform on the …

Finding errors in machine learning applications requires a thorough exploration of their
behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the …

The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace,
making it difficult for novel researchers and practitioners to have a bird's-eye view picture of …

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the
model's capabilities by employing prior knowledge and experience. A meta-learning …