Artificial intelligence (AI) and algorithmic decision making are having a profound impact on
our daily lives. These systems are vastly used in different high-stakes applications like …

Supervised learning algorithms have shown limited use in the field of anomaly detection due
to the unpredictability and difficulty in acquiring abnormal samples. In recent years …

In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights …

Abstract Language models learn a great quantity of factual information during pretraining,
and recent work localizes this information to specific model weights like mid-layer MLP …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Abstract Machine learning (ML) techniques are often employed for the accurate prediction of
the compressive strength of concrete. Despite higher accuracy, previous ML models failed to …

We seek to learn models that we can interact with using high-level concepts: if the model did
not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the …

Nowadays, deep neural networks are widely used in mission critical systems such as
healthcare, self-driving vehicles, and military which have direct impact on human lives …

The recent release of large-scale healthcare datasets has greatly propelled the research of
data-driven deep learning models for healthcare applications. However, due to the nature of …