Related papers: INDCOR white paper 4: Evaluation of Interactive Na…
In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…
There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…
Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g.,…
This paper describes the architecture of R&D Analyst, a commercial intelligent decision system for evaluating corporate research and development projects and portfolios. In analyzing projects, R&D Analyst interactively guides a user in…
We present an interpretability framework for unsupervised reinforcement learning (URL) agents, aimed at understanding how intrinsic motivation shapes attention, behavior, and representation learning. We analyze five agents DQN, RND, ICM,…
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a…
Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…
Data-driven stories seek to inform and persuade audiences through the use of data visualisations and engaging narratives. These stories have now been highly optimised to be viewed on desktop and mobile computers. In contrast, while…
Narratives serve as fundamental frameworks in our understanding of the world and play a crucial role in collaborative sensemaking, providing a versatile foundation for sensemaking. Framing is a subtle yet potent mechanism that influences…
Deep Neural Networks have been successfully used for the task of Visual Question Answering for the past few years owing to the availability of relevant large scale datasets. However these datasets are created in artificial settings and…
In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet…
With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While…
Developing robust and interpretable vision systems is a crucial step towards trustworthy artificial intelligence. In this regard, a promising paradigm considers embedding task-required invariant structures, e.g., geometric invariance, in…
This review addresses the problem of learning abstract representations of the measurement data in the context of Deep Reinforcement Learning (DRL). While the data are often ambiguous, high-dimensional, and complex to interpret, many…
Data-driven storytelling has gained prominence in journalism and other data reporting fields. However, the process of creating these stories remains challenging, often requiring the integration of effective visualizations with compelling…
Implicit Neural Representation (INR) has been emerging in computer vision in recent years. It has been shown to be effective in parameterising continuous signals such as dense 3D models from discrete image data, e.g. the neural radius field…
Explanations for computer vision models are important tools for interpreting how the underlying models work. However, they are often presented in static formats, which pose challenges for users, including information overload, a gap between…
Image Captioning (IC) has achieved astonishing developments by incorporating various techniques into the CNN-RNN encoder-decoder architecture. However, since CNN and RNN do not share the basic network component, such a heterogeneous…
We propose an approach for interactive learning for an image captioning model. As human feedback is expensive and modern neural network based approaches often require large amounts of supervised data to be trained, we envision a system that…
Despite recent advances in the field of explainable artificial intelligence systems, a concrete quantitative measure for evaluating the usability of such systems is nonexistent. Ensuring the success of an explanatory interface in…