Related papers: Towards Best Practice in Explaining Neural Network…

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…

The task of quantifying the inherent uncertainty associated with neural network predictions is a key challenge in artificial intelligence. Bayesian neural networks (BNNs) and deep ensembles are among the most prominent approaches to tackle…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

Increasingly complex learning methods such as boosting, bagging and deep learning have made ML models more accurate, but harder to understand and interpret. A tradeoff between performance and intelligibility is often to be faced, especially…

Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant…

We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and self-supervised…

While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these…

Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system,…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…

This paper is about a machine learning approach based on the multilinear projection of an unknown function (or probability distribution) to be estimated towards a linear (or multilinear) dimensional space E'. The proposal transforms the…

Memory, as the basis of learning, determines the storage, update and forgetting of knowledge and further determines the efficiency of learning. Featured with the mechanism of memory, a radial basis function neural network based learning…

Deep Reinforcement Learning (DRL) is a frequently employed technique to solve scheduling problems. Although DRL agents ace at delivering viable results in short computing times, their reasoning remains opaque. We conduct a case study where…

When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representations. Recently…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Both humans and machine learning models learn from experience, particularly in safety- and reliability-critical domains. While psychology seeks to understand human cognition, the field of Explainable AI (XAI) develops methods to interpret…

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model…

With the advent of deep learning, the number of works proposing new methods or improving existent ones has grown exponentially in the last years. In this scenario, "very deep" models were emerging, once they were expected to extract more…

Human action recognition involves the characterization of human actions through the automated analysis of video data and is integral in the development of smart computer vision systems. However, several challenges like dynamic backgrounds,…