Related papers: This looks more like that: Enhancing Self-Explaini…

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…

Despite their renowned predictive power on i.i.d. data, convolutional neural networks are known to rely more on high-frequency patterns that humans deem superficial than on low-frequency patterns that agree better with intuitions about what…

Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel…

To reduce the heavy computational burden of reactive power optimization of distribution networks, machine learning models are receiving increasing attention. However, most machine learning models (e.g., neural networks) are usually…

Neural networks, with powerful nonlinear mapping and classification capabilities, are widely applied in mechanical fault diagnosis to ensure safety. However, being typical black-box models, their application is limited in…

There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing…

Overfit is a fundamental problem in machine learning in general, and in deep learning in particular. In order to reduce overfit and improve generalization in the classification of images, some employ invariance to a group of…

Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern…

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

Tasks in Predictive Business Process Monitoring (PBPM), such as Next Activity Prediction, focus on generating useful business predictions from historical case logs. Recently, Deep Learning methods, particularly sequence-to-sequence models…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Prototypal analysis is introduced to overcome two shortcomings of archetypal analysis: its sensitivity to outliers and its non-locality, which reduces its applicability as a learning tool. Same as archetypal analysis, prototypal analysis…

Kernel pruning methods have been proposed to speed up, simplify, and improve explanation of convolutional neural network (CNN) models. However, the effectiveness of a simplified model is often below the original one. In this letter, we…

Part-prototype networks (e.g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts. However, recent works find that the…

This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we…

Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool…

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…

Deep neural networks (DNNs) have been shown to outperform traditional machine learning algorithms in a broad variety of application domains due to their effectiveness in modeling complex problems and handling high-dimensional datasets. Many…

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…