xai thesis

Explainable Artificial Intelligence (XAI) is an emerging area of research in the field of Artificial Intelligence (AI). XAI can explain how AI obtained a particular solution (e.g., classification or object detection) and can also answer other "wh" questions. This explainability is not possible in traditional AI. Explainability is essential for critical applications, such as defense, health ...

The much-hyped term in present era Explainable-Artificial Intelligence (XAI) can be traced back to the root and core researches produced by Scott [] where they deduced the importance of explaining certain decisions via a rule-based approach taking into consideration the variables that are in play.Multiple research work by Scott and Shortlife [22,23,24] confirms that the building blocks of XAI ...

1.1. The black-box issue and solution. The AI community is more concerned about the black-box issue following the establishment of rules for trustworthy AIs that are safe to use. eXplainable Artificial Intelligence (XAI) techniques are aimed at producing ML models with a good interpretability-accuracy tradeoff via: (i) building white/gray-box ML models which are interpretable by design (at ...

Grounded on a first elaboration of concepts and terms used in XAI-related research, we propose a novel definition of explainability that places audience (Fig. 2) as a key aspect to be considered when explaining a ML model.We also elaborate on the diverse purposes sought when using XAI techniques, from trustworthiness to privacy awareness, which round up the claimed importance of purpose and ...

As XAI is an emerging topic for construction, opportunities for future research are proposed (Section 4) before concluding the paper (Section 5). 2.0 Explainable AI An overview of how AI is applied in construction compared to XAI is presented in Figure 1 to provide a context for the paper and subsequent review. Underpinning XAI is the precepts of

The rapid growth and use of artificial intelligence (AI)-based systems have raised concerns regarding explainability. Recent studies have discussed the emerging demand for explainable AI (XAI); however, a systematic review of explainable artificial intelligence from an end user's perspective can provide a comprehensive understanding of the current situation and help close the research gap.

consequently explainable artificial intelligence, henceforth also known as XAI. Explainability aims to absolve artificial intelligence systems of any doubt and validate those systems to be used in fields where mistakes cannot be tolerated. This thesis explores the explainability of multi-layer perceptron networks and how their

TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP. While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training.

This paper addresses how people understand Explainable Artificial Intelligence (XAI) in three ways: contrastive, functional, and transparent. We discuss the unique aspects and challenges of each ...

Eventually, a comprehensive framework of XAI and its possible effects on user behavior has been put together in our work. Discover the world's research. 25+ million members;

an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural. Networks) that were not present in the last hype of AI (namely, expert systems and rule based ...

Master thesis announcement Title: Evaluating the explanation of black box decision for text classification Description Explainable AI (XAI) is artificial intelligence in which the results of the solution can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even its designers

Discussion: The developers compared GraphLIME with one of the first xAI methods for GNNs at the time, namely GNNExplainer, w.r.t. three criteria: (1) ability to detect useless features, (2) ability to decide whether the prediction is trustworthy, and (3) ability to identify the better model among two GNN classifiers.

This thesis aims to provide the background of XAI and the summary of latest achievements in the field in the form of literature review. The following research questions are considered: What kind of explanation techniques have already been implemented in the field of XAI? Are

A framework of XAI criteria is introduced to classify deep learning-based medical image analysis methods. Papers on XAI techniques in medical image analysis are then surveyed and categorized according to the framework and according to anatomical location. The paper concludes with an outlook of future opportunities for XAI in medical image analysis.

XAI refers to methods and techniques in the application of artificial intelligence (AI) such that the results of the solution can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even its designers cannot explain why an AI arrived at a specific decision. XAI may be an implementation of the social right to explanation. XAI is relevant even if ...

This research paper explores Explainable Artificial Intelligence (XAI) and its application in healthcare, with a specific focus on transparent models designed for clinical decision support in various medical disciplines. The paper initiates by underscoring the crucial requirement for transparency and interpretability in AI systems within the ...

The past decade has seen significant progress in artificial intelligence (AI), which has resulted in algorithms being adopted for resolving a variety of problems. However, this success has been met by increasing model complexity and employing black-box AI models that lack transparency. In response to this need, Explainable AI (XAI) has been proposed to make AI more transparent and thus advance ...

Explainable AI (XAI): A survey of recents methods, applications and frameworks. Deep learning applications have drawn a lot of attention since they have surpassed humans in many tasks such as image and speech recognition, and recommendation systems. However, these applications lack explainability and reliability.

The 5 XAIresearch lines. The XAI project faces the challenge of requiring AI to be explainable and understandable in human terms and articulates its research along 5 Research Activities: 1 algorithms to infer local explanations and their generalization to global ones (post-hoc) and algorithms that are transparent by-design; 2 languages for ...

Tobias Archut from the xAI Lab Bamberg receives DMEA Newcomer Award for advancing digital healthcare through his innovative bachelor thesis In a celebration of burgeoning talent within the digital healthcare sphere, Tobias Archut, one of xAI Lab's promising students, clinched third place at the esteemed DMEA Newcomer Award.

My investment thesis remains Bearish on the stock, ... Even at $30K a GPU, xAI would spend $2.4 billion on the 80K additional GPUs, but the company is only buying 80,000 GPUs. A large corporation ...