Related papers: Rashomon Sets for Prototypical-Part Networks: Edit…

Given thousands of equally accurate machine learning (ML) models, how can users choose among them? A recent ML technique enables domain experts and data scientists to generate a complete Rashomon set for sparse decision trees--a huge set of…

Kernel methods provide a flexible and theoretically grounded approach to nonlinear and nonparametric learning. While memory and run-time requirements hinder their applicability to large datasets, many low-rank kernel approximations, such as…

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpretable concepts (``the bottleneck'') and use the concepts to make predictions. A concept bottleneck enhances interpretability since it can be investigated to understand…

The Rashomon effect describes the observation that in machine learning (ML) multiple models often achieve similar predictive performance while explaining the underlying relationships in different ways. This observation holds even for…

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

While interpretable prototype networks offer compelling case-based reasoning for clinical diagnostics, their raw continuous outputs lack the semantic structure required for medical documentation. Bridging this gap via standard…

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a…

There are two things to be considered when we evaluate predictive models. One is prediction accuracy,and the other is interpretability. Over the recent decades, many prediction models of high performance, such as ensemble-based models and…

Current machine learning has made great progress on computer vision and many other fields attributed to the large amount of high-quality training samples, while it does not work very well on genomic data analysis, since they are notoriously…

Neural network architectures are most often conceptually designed and described in visual terms, but are implemented by writing error-prone code. PrototypeML is a machine learning development environment that bridges the dichotomy between…

Explainable Artificial Intelligence (xAI) has the potential to enhance the transparency and trust of AI-based systems. Although accurate predictions can be made using Deep Neural Networks (DNNs), the process used to arrive at such…

Deep learning methods, in particular convolutional neural networks, have emerged as a powerful tool in medical image computing tasks. While these complex models provide excellent performance, their black-box nature may hinder real-world…

Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate…

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Deep learning models have significantly advanced acoustic bird monitoring by being able to recognize numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into…

Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image "looks like" a prototype. However, perceptual similarity for humans…

Object detection in aerial images is a fundamental research topic in the geoscience and remote sensing domain. However, the advanced approaches on this topic mainly focus on designing the elaborate backbones or head networks but ignore neck…

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias within the dataset as the cue to improve performance. When a…

This paper describes a method of online refinement of a scene recognition model for robot navigation considering traversable plants, flexible plant parts which a robot can push aside while moving. In scene recognition systems that consider…