Relevant bibliographies by topics / Diverse explanations

Academic literature on the topic 'Diverse explanations'

Author: Grafiati
Published: 18 May 2024

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Contents

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Diverse explanations.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Diverse explanations"

1

Ley, Dan, Umang Bhatt, and Adrian Weller. "Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7390–98. http://dx.doi.org/10.1609/aaai.v36i7.20702.

Full text
Abstract:
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain. We broaden the exploration to examine δ-CLUE, the set of potential CLUEs within a δ ball of the original input in latent space. We study the diversity of such sets and find that many CLUEs are redundant; as such, we propose DIVerse CLUE (∇-CLUE), a set of CLUEs which each propose a distinct explanation as to how one can decrease the uncertainty associated with an input. We then further propose GLobal AMortised CLUE (GLAM-CLUE), a distinct, novel method which learns amortised mappings that apply to specific groups of uncertain inputs, taking them and efficiently transforming them in a single function call into inputs for which a model will be certain. Our experiments show that δ-CLUE, ∇-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.
APA, Harvard, Vancouver, ISO, and other styles
2

Yang, Mengyuan, Mengying Zhu, Yan Wang, Linxun Chen, Yilei Zhao, Xiuyuan Wang, Bing Han, Xiaolin Zheng, and Jianwei Yin. "Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 8 (March 24, 2024): 9250–59. http://dx.doi.org/10.1609/aaai.v38i8.28777.

Full text
Abstract:
Large language model-based explainable recommendation (LLM-based ER) systems can provide remarkable human-like explanations and have widely received attention from researchers. However, the original LLM-based ER systems face three low-quality problems in their generated explanations, i.e., lack of personalization, inconsistency, and questionable explanation data. To address these problems, we propose a novel LLM-based ER model denoted as LLM2ER to serve as a backbone and devise two innovative explainable quality reward models for fine-tuning such a backbone in a reinforcement learning paradigm, ultimately yielding a fine-tuned model denoted as LLM2ER-EQR, which can provide high-quality explanations. LLM2ER-EQR can generate personalized, informative, and consistent high-quality explanations learned from questionable-quality explanation datasets. Extensive experiments conducted on three real-world datasets demonstrate that our model can generate fluent, diverse, informative, and highly personalized explanations.
APA, Harvard, Vancouver, ISO, and other styles
3

Cho, Hyeoncheol, Youngrock Oh, and Eunjoo Jeon. "SEEN: Seen: Sharpening Explanations for Graph Neural Networks Using Explanations From Neighborhoods." Advances in Artificial Intelligence and Machine Learning 03, no. 02 (2023): 1165–79. http://dx.doi.org/10.54364/aaiml.2023.1168.

Full text
Abstract:
Explaining the foundations for predictions obtained from graph neural networks (GNNs) is critical for credible use of GNN models for real-world problems. Owing to the rapid growth of GNN applications, recent progress in explaining predictions from GNNs, such as sensitivity analysis, perturbation methods, and attribution methods, showed great opportunities and possibilities for explaining GNN predictions. In this study, we propose a method to improve the explanation quality of node classification tasks that can be applied in a post hoc manner through aggregation of auxiliary explanations from important neighboring nodes, named SEEN. Applying SEEN does not require modification of a graph and can be used with diverse explainability techniques due to its independent mechanism. Experiments on matching motifparticipating nodes from a given graph show great improvement in explanation accuracy of up to 12.71% and demonstrate the correlation between the auxiliary explanations and the enhanced explanation accuracy through leveraging their contributions. SEEN provides a simple but effective method to enhance the explanation quality of GNN model outputs, and this method is applicable in combination with most explainability techniques.
APA, Harvard, Vancouver, ISO, and other styles
4

Sanneman, Lindsay. "Understanding Our Robots With the Help of Human-Centered Explainable AI." XRDS: Crossroads, The ACM Magazine for Students 30, no. 1 (September 2023): 52–57. http://dx.doi.org/10.1145/3611686.

Full text
Abstract:
Insights from the field of human factors can help us design human-centered explanations that enable effective human-robot interaction. Studying explanation techniques according to these human factors will be critical in understanding their efficacy across diverse contexts.
APA, Harvard, Vancouver, ISO, and other styles
5

Sorto, M. Alejandra, Carlos A. Mejía Colindres, and Aaron T. Wilson. "Informing Practice: Uncovering and Eliciting Perceptions in Linguistically Diverse Classrooms." Mathematics Teaching in the Middle School 20, no. 2 (September 2014): 72–77. http://dx.doi.org/10.5951/mathteacmiddscho.20.2.0072.

Full text
Abstract:
One of the many challenges that teachers face in mathematics classrooms is determining how much of the verbal and written explanations help students accomplish instructional goals. The challenge is greater in linguistically diverse classrooms because the explanations and multiple representations are not perceived uniformly by all students.
APA, Harvard, Vancouver, ISO, and other styles
6

Clark, Stephen R. L. "Supernatural Explanations and Inspirations." European Journal for Philosophy of Religion 9, no. 3 (September 21, 2017): 49–63. http://dx.doi.org/10.24204/ejpr.v9i3.1990.

Full text
Abstract:
I propose, in partial response to the rich essays by Millican & Thornhill-Miller and Salamon that religious traditions are too diverse to be represented either by a cosmological core or even (though this is more plausible) an ethical. Religious sensibility is more often inspirational than explanatory, does not always require a transcendent origin of all things (however reasonable that thesis may be in the abstract), and does not always support the sort of humanistic values preferred in the European Enlightenment. A widely shared global religion is more likely to be eclectic than carefully ‘rational’, and is likely to be opposed by a more overtly ‘supernatural’ project founded in revelation.
APA, Harvard, Vancouver, ISO, and other styles
7

Wang, Linlin, Zefeng Cai, Gerard De Melo, Zhu Cao, and Liang He. "Disentangled CVAEs with Contrastive Learning for Explainable Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 11 (June 26, 2023): 13691–99. http://dx.doi.org/10.1609/aaai.v37i11.26604.

Full text
Abstract:
Modern recommender systems are increasingly expected to provide informative explanations that enable users to understand the reason for particular recommendations. However, previous methods struggle to interpret the input IDs of user--item pairs in real-world datasets, failing to extract adequate characteristics for controllable generation. To address this issue, we propose disentangled conditional variational autoencoders (CVAEs) for explainable recommendation, which leverage disentangled latent preference factors and guide the explanation generation with the refined condition of CVAEs via a self-regularization contrastive learning loss. Extensive experiments demonstrate that our method generates high-quality explanations and achieves new state-of-the-art results in diverse domains.
APA, Harvard, Vancouver, ISO, and other styles
8

Li, Dingbang, Wenzhou Chen, and Xin Lin. "MSGeN: Multimodal Selective Generation Network for Grounded Explanations." Electronics 13, no. 1 (December 29, 2023): 152. http://dx.doi.org/10.3390/electronics13010152.

Full text
Abstract:
Modern models have shown impressive capabilities in visual reasoning tasks. However, the interpretability of their decision-making processes remains a challenge, causing uncertainty in their reliability. In response, we present the Multimodal Selective Generation Network (MSGeN), a novel approach to enhancing interpretability and transparency in visual reasoning. MSGeN can generate explanations that seamlessly integrate diverse modal information, providing a comprehensive and intuitive understanding of its decisions. The model consists of five collaborative components: (1) the Multimodal Encoder, which encodes and fuses input data; (2) the Reasoner, which is responsible for generating stepwise inference states; (3) the Selector, which is utilized for selecting the modality for each step’s explanation; (4) the Speaker, which generates natural language descriptions; and (5) the Pointer, which produces visual cues. These components work harmoniously to generate explanations enriched with natural language context and visual cues. Our extensive experimentation demonstrates that MSGeN surpasses existing multimodal explanation generation models across various metrics, including BLEU, METEOR, ROUGE, CIDEr, SPICE, and Grounding. We also show detailed visual examples highlighting MSGeN’s ability to generate comprehensive and coherent explanations, showcasing its effectiveness through practical case studies.
APA, Harvard, Vancouver, ISO, and other styles
9

Santos, Daniel, José Augusto Baranauskas, and Renato Tinós. "Local Rule-Based Explanations Method Based on Genetic Algorithms with Fitness Sharing." Learning and Nonlinear Models 21, no. 2 (September 7, 2023): 4–15. http://dx.doi.org/10.21528/lnlm-vol21-no2-art1.

Full text
Abstract:
The Local Rule Based Explanations method (LORE) explains decisions of black-box classifiers by using an interpretable model (Decision Tree – DT). The DT is trained with an artificial dataset generated by Genetic Algorithms (GAs). The primary objective of this approach is to replicate the decision boundaries of the black-box model in proximity to the instance under explanation. We show that the artificial examples generated by the GAs in LORE are not necessarily diverse. Consequently, we propose the integration of GAs with fitness sharing in LORE to generate a more diversified subset of artificial examples. The underlying motivation is to ensure that the local decision boundaries of the DT more closely resemble those of the black-box classifier. Experimental results with two classifiers (Multilayer Perceptron and Random Forests), and four classification problems, indicate that LORE with fitness sharing yields more diverse GA populations, consequently leading to improved local explanations. These findings underscore the effectiveness of incorporating fitness sharing into the LORE methodology for enhancing the explainability of black-box classifiers.
APA, Harvard, Vancouver, ISO, and other styles
10

Rožanec, Jože, Elena Trajkova, Inna Novalija, Patrik Zajec, Klemen Kenda, Blaž Fortuna, and Dunja Mladenić. "Enriching Artificial Intelligence Explanations with Knowledge Fragments." Future Internet 14, no. 5 (April 29, 2022): 134. http://dx.doi.org/10.3390/fi14050134.

Full text
Abstract:
Artificial intelligence models are increasingly used in manufacturing to inform decision making. Responsible decision making requires accurate forecasts and an understanding of the models’ behavior. Furthermore, the insights into the models’ rationale can be enriched with domain knowledge. This research builds explanations considering feature rankings for a particular forecast, enriching them with media news entries, datasets’ metadata, and entries from the Google knowledge graph. We compare two approaches (embeddings-based and semantic-based) on a real-world use case regarding demand forecasting. The embeddings-based approach measures the similarity between relevant concepts and retrieved media news entries and datasets’ metadata based on the word movers’ distance between embeddings. The semantic-based approach recourses to wikification and measures the Jaccard distance instead. The semantic-based approach leads to more diverse entries when displaying media events and more precise and diverse results regarding recommended datasets. We conclude that the explanations provided can be further improved with information regarding the purpose of potential actions that can be taken to influence demand and to provide “what-if” analysis capabilities.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Diverse explanations"

1

Jeyasothy, Adulam. "Génération d'explications post-hoc personnalisées." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS027.

Full text
Abstract:
La thèse se place dans le domaine de l'IA explicable (XAI, eXplainable AI). Nous nous concentrons sur les méthodes d'interprétabilité post-hoc qui visent à expliquer à un utilisateur la prédiction pour une donnée d'intérêt spécifique effectuée par un modèle de décision entraîné. Pour augmenter l'interprétabilité des explications, cette thèse étudie l'intégration de connaissances utilisateur dans ces méthodes, et vise ainsi à améliorer la compréhensibilité de l'explication en générant des explications personnalisées adaptées à chaque utilisateur. Pour cela, nous proposons un formalisme général qui intègre explicitement la connaissance via un nouveau critère dans les objectifs d'interprétabilité. Ce formalisme est ensuite décliné pour différents types connaissances et différents types d'explications, particulièrement les exemples contre-factuels, conduisant à la proposition de plusieurs algorithmes (KICE, Knowledge Integration in Counterfactual Explanation, rKICE pour sa variante incluant des connaissances exprimées par des règles et KISM, Knowledge Integration in Surrogate Models). La question de l'agrégation des contraintes de qualité classique et de compatibilité avec les connaissances est également étudiée et nous proposons d'utiliser l'intégrale de Gödel comme opérateur d'agrégation. Enfin nous discutons de la difficulté à générer une unique explication adaptée à tous types d'utilisateurs et de la notion de diversité dans les explications
This thesis is in the field of eXplainable AI (XAI). We focus on post-hoc interpretability methods that aim to explain to a user the prediction for a specific data made by a trained decision model. To increase the interpretability of explanations, this thesis studies the integration of user knowledge into these methods, and thus aims to improve the understandability of the explanation by generating personalized explanations tailored to each user. To this end, we propose a general formalism that explicitly integrates knowledge via a new criterion in the interpretability objectives. This formalism is then declined for different types of knowledge and different types of explanations, particularly counterfactual examples, leading to the proposal of several algorithms (KICE, Knowledge Integration in Counterfactual Explanation, rKICE for its variant including knowledge expressed by rules and KISM, Knowledge Integration in Surrogate Models). The issue of aggregating classical quality and knowledge compatibility constraints is also studied, and we propose to use Gödel's integral as an aggregation operator. Finally, we discuss the difficulty of generating a single explanation suitable for all types of users and the notion of diversity in explanations
APA, Harvard, Vancouver, ISO, and other styles
2

Adler, J. Douglas. "Student observations and explanations of a physical phenomenon : the Cartesian Diver." Thesis, 1997. http://hdl.handle.net/2429/6412.

Full text
Abstract:
This study explored student observations and explanations of the Cartesian Diver. The study was conducted in a Grade 6/7 class in the lower mainland of Vancouver it. chronicled and categorized the developing understanding of three pairs of students. Each dyad participated in four events. Each event presented a unique variation of the Cartesian Diver. The first and third event involved a working Cartesian Diver, while events two and four required the students to construct a Cartesian Diver. Throughout the events, the researcher videotaped each pair's manipulations, observations and explanations. The data was analyzed using two established frameworks (Gunstone, 1998; Frazier, 1995). Students were able to construct a working Cartesian Diver and offer many explanations for its functioning. Student explanations of the Cartesian Diver were constructed from the data. The number of explanations increased as the students became familiar with the equipment and the variables which determine the behaviour of the Cartesian Diver. While many of the explanations were scientific, the students could only explain what they saw; student theories were context driven. None of the students was able to formulate a comprehensive theory to explain the Cartesian Diver.
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "Diverse explanations"

1

Unger, Daniel M. Titian’s Allegory of Marriage. Nieuwe Prinsengracht 89 1018 VR Amsterdam Nederland: Amsterdam University Press, 2022. http://dx.doi.org/10.5117/9789463729536.

Full text
Abstract:
This book offers nine new approaches toward a single work of art, Titian’s Allegory of Marriage or Allegory of Alfonso d’Avalos, dated to 1530/5. In earlier references, the painting was named simply Allegory, alluding to its enigmatic nature. The work follows in a tradition of such ambiguous Venetian paintings as Giovanni Bellini’s Sacred Allegory and Giorgione’s Tempest. Throughout the years, Titian’s Allegory has engendered a range of diverse interpretations. Art historians such as Hans Tietze, Erwin Panofsky, Walter Friedlaender, and Louis Hourticq, to mention only a few, promoted various explanations. This book offers novel approaches and suggests new meanings toward a further understanding of this somewhat abstruse painting.
APA, Harvard, Vancouver, ISO, and other styles
2

Ullmann-Margalit, Edna. Invisible-Hand Explanations. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780198802433.003.0008.

Full text
Abstract:
Invisible-hand explanations suggest that many social practices are a product of human action, but not human design. In coming to terms with such explanations, it is essential to distinguish between explanations of the emergence of practices and explanations of the persistence of practices. The kind of invisible-hand explanation that accounts for the emergence of practices might turn out to be altogether different from the kind that accounts for their persistence. The emergence of practices is often best explained by aggregating explanations: Diverse and dispersed action by numerous people might produce some kind of pattern, even if they did not foresee it or intend to bring it about. By contrast, practices often persist because of evolutionary explanations. They survive some sort of competition. Survival value may have nothing to do with the emergence of a practice in the first place.
APA, Harvard, Vancouver, ISO, and other styles
3

Kaplan, David M. Neural Computation, Multiple Realizability, and the Prospects for Mechanistic Explanation. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780199685509.003.0008.

Full text
Abstract:
There is an ongoing philosophical and scientific debate concerning the nature of computational explanation in the neurosciences. Recently, some have cited modeling work involving so-called canonical neural computations—standard computational modules that apply the same fundamental operations across multiple brain areas—as evidence that computational neuroscientists sometimes employ a distinctive explanatory scheme from that of mechanistic explanation. Because these neural computations can rely on diverse circuits and mechanisms, modeling the underlying mechanisms is supposed to be of limited explanatory value. I argue that these conclusions about computational explanations in neuroscience are mistaken, and rest upon a number of confusions about the proper scope of mechanistic explanation and the relevance of multiple realizability considerations. Once these confusions are resolved, the mechanistic character of computational explanations can once again be appreciated.
APA, Harvard, Vancouver, ISO, and other styles
4

Robinson, Paul H., and Tyler Scot Williams. Mapping American Criminal Law. ABC-CLIO, LLC, 2018. http://dx.doi.org/10.5040/9798400682667.

Full text
Abstract:
Containing 40 visually coded maps of the fifty states, this book offers an unprecedented look at America's diverse legal landscape. This first-of-its-kind volume sketches the diversity implicit in United States criminal law doctrine through its examination of a range of criminal laws pertaining to murder, sexual assault, drug offenses, the insanity defense, and more and the way in which different states deal with those issues. In addition to providing insights into the most widely invoked standards in criminal law, it raises awareness of the enormous discrepancies among the criminal laws of states, documenting them using dozens of visually coded maps that showcase geographic, political, and socioeconomic differences to explain patterns of agreement and disagreement. Mapping American Criminal Law: Variations Across the 50 States is for political scientists, criminologists, sociologists, legal scholars, policy advisors, legislators, lawyers, judges, and scholars and students of these fields. In addition, each chapter is highly accessible to laypersons and includes an explanation of the subject matter as well as explanations of the various approaches to criminal law taken by states.
APA, Harvard, Vancouver, ISO, and other styles
5

Mendes, Paulo. Cooling Down: Local Responses to Global Climate Change. Edited by Susanna M. Hoffman and Thomas Hylland Eriksen. Berghahn Books, 2022. http://dx.doi.org/10.3167/9781800731899.

Full text
Abstract:
Climate change is a slowly advancing crisis sweeping over the planet and affecting different habitats in strikingly diverse ways. While nations have signed treaties and implemented policies, most actual climate change assessments, adaptations, and countermeasures take place at the local level. People are responding by adjusting their practices, livelihoods, and cultures, protesting and migrating. This book portrays the diversity of explanations and remedies as expressed at the community level and its emphasis on the crucial importance of ethnographic detail in demonstrating how people in different parts of the world are scaling down the phenomenon of global warming.
APA, Harvard, Vancouver, ISO, and other styles
6

Belsey, Catherine. Poststructuralism: A Very Short Introduction. 2nd ed. Oxford University PressOxford, 2022. http://dx.doi.org/10.1093/actrade/9780198859963.001.0001.

Full text
Abstract:
Abstract Poststructuralism challenges traditional ways of thinking about the relations between human beings, culture, and the world. Language and meaning are reappraised, and with them assumptions about what it is possible for us to know. Poststructuralism resists certainties and offers ways to consider our place in the world that compete with conventional explanations. In this Very Short Introduction, Catherine Belsey examines key figures such as Roland Barthes, Jacques Derrida, Michel Foucault, Julia Kristeva, Gilles Deleuze, and Sarah Kofman, drawing examples from sources as diverse as M. C. Escher, politics, Shakespeare, climate change, love, primatology, and pandemics.
APA, Harvard, Vancouver, ISO, and other styles
7

Gallagher, Sally K. Why Won’t Religion Just Go Away? Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780190239671.003.0001.

Full text
Abstract:
This chapter outlines explanations for the continuing salience of religion in the United States and raises questions about how congregations, including the structures in which they worship, contribute to adult identity for women and men. Beginning with an assessment of current theories of religious markets and religious subcultures, and theories of religious conversion or switching, we make the case that denominational distinctives continue to shape membership for women and men. We critique the generalization that women are more religious than men, and we provide a brief overview of the analysis of how women and men experience the process of joining, growing connection and involvement, and changing within three diverse congregations.
APA, Harvard, Vancouver, ISO, and other styles
8

Englehardt, Joshua D., Verenice Y. Heredia Espinoza, and Christopher S. Beekman, eds. Ancient West Mexicos. University Press of Florida, 2020. http://dx.doi.org/10.5744/florida/9780813066349.001.0001.

Full text
Abstract:
Ancient west Mexico has often been viewed as an isolated mishmash of cultures, separated from Mesoamerica “proper,” a region that lacked “civilization.” This volume argues against this vision by highlighting current archaeological research on the diverse and complex pre-Hispanic societies that developed in this area. Through the presentation of original data and interpretations, contributions provoke debate and advance understanding of regional complexity, chronology, and diversity, as well as the role of the west in broader, pan-Mesoamerican sociocultural processes. The volume illustrates the ways in which research and areal data from western Mesoamerica can meaningfully contribute to the construction of theoretical models applicable in multiple contexts and capable of enhancing archaeological descriptions and explanations of the dynamic diversity characteristic of all Mesoamerican societies. The volume also presents intriguing case studies from western Mesoamerica that illuminate alternative pathways to sociopolitical complexity in pre-Hispanic societies. In doing so, the volume seeks to contribute to contemporary anthropological and archaeological debates regarding the ways in which archaeologists describe and explain the material configurations that they encounter in the archaeological record, and how these configurations may explain, relate to, and enhance our understanding of the ancient lifeways of the diverse societies that inhabited the region.
APA, Harvard, Vancouver, ISO, and other styles
9

Colella, Adrienne J., and Eden B. King, eds. The Oxford Handbook of Workplace Discrimination. Oxford University Press, 2015. http://dx.doi.org/10.1093/oxfordhb/9780199363643.001.0001.

Full text
Abstract:
Increasing workplace diversity has given rise to growing intergroup challenges that persistently manifest in discrimination. An emerging science in psychology, sociology, and management has yielded useful evidence to be brought to bear on the important problem of discrimination, but most literature available focuses on social (rather than work) settings or legal (rather than interpersonal) issues, or focuses on the general phenomenon of diversity rather than the social problem of discrimination. The Oxford Handbook of Workplace Discrimination provides a broad and interdisciplinary review of state-of-the-art research on discrimination in the workplace. Contributing authors address the unique experience of people from diverse perspectives (such as religious minorities, gay and lesbian workers, and those with disabilities) and the ways in which discrimination can be manifested and its consequences, and offer explanations for discrimination and strategies for its reduction.
APA, Harvard, Vancouver, ISO, and other styles
10

Wright, Kenneth W. Pediatric Ophthalmology for Primary Care, 3rd Ed. American Academy of Pediatrics, 2007. http://dx.doi.org/10.1542/9781581104363.

Full text
Abstract:
Formatted for practical problem solving, the new 3rd edition of this clinical resource manual covers the full spectrum of eye disorders, eye examinations, vision screening, strabismus, dyslexia, ocular trauma, genetic syndromes, and all the diverse pediatric-specific eye disorders you are likely to encounter. "This book is a useful and well presented source of pediatric ophthalmology. The excellent photos are clear and crisp." Stephen Mikell, MD, Ochsner Clinic Foundation, Doody's Review, 2008. Clear, concise explanations and recommendations are complemented by numerous figures and photographs demonstrating eye pathology. Includes more than 200 color images; ready access to expert guidance through all the steps in effective diagnosis and intervention, including laboratory workup, etiology, differential diagnosis, preferred treatment approach, clinical course, prognosis, and indications for referral; expanded chapter on amblyopia and strabismus; new information on the importance of maintaining physiologic hypoxia; and down syndrome.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "Diverse explanations"

1

Smyth, Barry, and Mark T. Keane. "A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations." In Case-Based Reasoning Research and Development, 18–32. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-14923-8_2.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

García Portilla, Jason. "Conditions (Predictor Variables): Theories Explaining Prosperity Differences (B), (C), (D), (E)." In “Ye Shall Know Them by Their Fruits”, 35–57. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-78498-0_5.

Full text
Abstract:
AbstractThis chapter defines the conditions elements of the research model in this study (Fig. 10.1007/978-3-030-78498-0_2#Fig1). Therefore, Sects. 5.1–5.7 refer to some influential theories that have sought to explain differences in prosperity between countries from diverse disciplinary perspectives. Potential prosperity factors/theories can be clustered into three groups: (1) cultural and religious values; (2) institutions and economic growth; (3) environment and geography. Each of these distinct theories may contain “a grain of truth” about understanding prosperity imbalances between countries. Ideally, prosperity theories should be complementary instead of competing explanations. For example, geography and environmental theories explain how seasonal lands can provide a society and its economy better conditions to prosper. Institutional theory helps explain how institutions model social prosperity by perpetuating equality loops or by concentrating wealth. Cultural theory contributes to the understanding of the influence of cultural variables, such as religious beliefs and values, on prosperity. Yet, the relations among environment/geography, culture, institutions, and prosperity are highly complex and involve massive historical dynamics which would normally far exceed the scope of empirical research.
APA, Harvard, Vancouver, ISO, and other styles
3

Holzinger, Andreas, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, and Wojciech Samek. "xxAI - Beyond Explainable Artificial Intelligence." In xxAI - Beyond Explainable AI, 3–10. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-04083-2_1.

Full text
Abstract:
AbstractThe success of statistical machine learning from big data, especially of deep learning, has made artificial intelligence (AI) very popular. Unfortunately, especially with the most successful methods, the results are very difficult to comprehend by human experts. The application of AI in areas that impact human life (e.g., agriculture, climate, forestry, health, etc.) has therefore led to an demand for trust, which can be fostered if the methods can be interpreted and thus explained to humans. The research field of explainable artificial intelligence (XAI) provides the necessary foundations and methods. Historically, XAI has focused on the development of methods to explain the decisions and internal mechanisms of complex AI systems, with much initial research concentrating on explaining how convolutional neural networks produce image classification predictions by producing visualizations which highlight what input patterns are most influential in activating hidden units, or are most responsible for a model’s decision. In this volume, we summarize research that outlines and takes next steps towards a broader vision for explainable AI in moving beyond explaining classifiers via such methods, to include explaining other kinds of models (e.g., unsupervised and reinforcement learning models) via a diverse array of XAI techniques (e.g., question-and-answering systems, structured explanations). In addition, we also intend to move beyond simply providing model explanations to directly improving the transparency, efficiency and generalization ability of models. We hope this volume presents not only exciting research developments in explainable AI but also a guide for what next areas to focus on within this fascinating and highly relevant research field as we enter the second decade of the deep learning revolution. This volume is an outcome of the ICML 2020 workshop on “XXAI: Extending Explainable AI Beyond Deep Models and Classifiers.”
APA, Harvard, Vancouver, ISO, and other styles
4

Holzinger, Andreas, Anna Saranti, Anne-Christin Hauschild, Jacqueline Beinecke, Dominik Heider, Richard Roettger, Heimo Mueller, Jan Baumbach, and Bastian Pfeifer. "Human-in-the-Loop Integration with Domain-Knowledge Graphs for Explainable Federated Deep Learning." In Lecture Notes in Computer Science, 45–64. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-40837-3_4.

Full text
Abstract:
AbstractWe explore the integration of domain knowledge graphs into Deep Learning for improved interpretability and explainability using Graph Neural Networks (GNNs). Specifically, a protein-protein interaction (PPI) network is masked over a deep neural network for classification, with patient-specific multi-modal genomic features enriched into the PPI graph’s nodes. Subnetworks that are relevant to the classification (referred to as “disease subnetworks”) are detected using explainable AI. Federated learning is enabled by dividing the knowledge graph into relevant subnetworks, constructing an ensemble classifier, and allowing domain experts to analyze and manipulate detected subnetworks using a developed user interface. Furthermore, the human-in-the-loop principle can be applied with the incorporation of experts, interacting through a sophisticated User Interface (UI) driven by Explainable Artificial Intelligence (xAI) methods, changing the datasets to create counterfactual explanations. The adapted datasets could influence the local model’s characteristics and thereby create a federated version that distils their diverse knowledge in a centralized scenario. This work demonstrates the feasibility of the presented strategies, which were originally envisaged in 2021 and most of it has now been materialized into actionable items. In this paper, we report on some lessons learned during this project.
APA, Harvard, Vancouver, ISO, and other styles
5

Rivadulla, Andrés. "The search for explanations in the methodology of mathematical physics." In De Diversis Artibus, 149–55. Turnhout: Brepols Publishers, 2002. http://dx.doi.org/10.1484/m.dda-eb.4.00606.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Tamayo, Lizeth I., Elam Day-Friedland, Valentina A. Zavala, Katie M. Marker, and Laura Fejerman. "Genetic Ancestry and Breast Cancer Subtypes in Hispanic/Latina Women." In Advancing the Science of Cancer in Latinos, 79–88. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-14436-3_7.

Full text
Abstract:
AbstractBreast cancer is the most common cancer among US Hispanics/Latinas; however, Hispanic/Latina women in the United States have historically shown a relatively low breast cancer incidence compared to non-Hispanic White or African American/Black women. Hispanics/Latinos are genetically diverse, with varying proportions of European, Indigenous American, African, and to a lesser extent, Asian continental genetic ancestry. This heterogeneous group has often been treated as a monolithic unit in cancer epidemiology, due to small sample sizes and the concomitant limitations in statistical power. Only a few breast cancer studies including Hispanics/Latinas have analyzed the correlation between individual genetic ancestry proportion and tumor subtype. Most of these studies were unable to provide conclusive evidence due to the reduced number of patients with available tumor subtype information (either from immunohistochemical markers or gene expression data). This chapter provides a brief description of results reported from breast cancer studies including US Hispanic/Latina or Latin American patients assessing the association/correlation between genetic ancestry and breast cancer subtype. Also discussed are possible explanations for reported findings and a perspective on how further studies could lead to more precise tumor subtype-specific risk assessment, treatment efficacy, and outcome prognosis in US Hispanics/Latinas and Latin American women.
APA, Harvard, Vancouver, ISO, and other styles
7

Kolek, Stefan, Duc Anh Nguyen, Ron Levie, Joan Bruna, and Gitta Kutyniok. "A Rate-Distortion Framework for Explaining Black-Box Model Decisions." In xxAI - Beyond Explainable AI, 91–115. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-04083-2_6.

Full text
Abstract:
AbstractWe present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations of the target input signal and applies to any differentiable pre-trained model such as neural networks. Our experiments demonstrate the framework’s adaptability to diverse data modalities, particularly images, audio, and physical simulations of urban environments.
APA, Harvard, Vancouver, ISO, and other styles
8

Cao, Tian Yu. "Ontology and scientific explanation." In Explanations, 173–96. Oxford University PressOxford, 2004. http://dx.doi.org/10.1093/oso/9780198607786.003.0010.

Full text
Abstract:
Abstract Over millennia, we humans have invented and developed a multiplicity of ways to understand whatever in the world intrigues us. These many modes of understanding include mythical projections, religious teachings, metaphysical speculations, magical association, hermeneutic readings, mathematical and logical reasoning, and scientific explanation. What differentiates scientific explanation from other modes of understanding is a question standing at the very centre of the philosophy of science, a question to which philosophers of various persuasions have different answers. In this short piece I am not, however, going to examine these diverse opinions beyond offering a few brief comments. Rather, my major concern is to give an outline of my own view of scientific explanation, which I will then illustrate by several examples taken mainly from physics.
APA, Harvard, Vancouver, ISO, and other styles
9

Obeng-Odoom, Franklin. "Problematic Explanations." In Global Migration beyond Limits, 20–36. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780198867180.003.0002.

Full text
Abstract:
The orthodoxy on analysing and addressing the migration question is diverse and complex, but in whatever version it comes, it is problematic. This chapter demonstrates this variety in the orthodoxy, offers fundamental critiques, and provides the grounds for reframing and addressing the migration question. The chapter accepts that there is substantial global migration, but it rejects as unsatisfactory the existing explanations of the mainstream conservative/nationalist, neoliberal, and humanist views, centred on various aspects of the thesis by Garrett Hardin and others, whose approach develop the ‘Chicago School of property rights’ (Haila, 2016, p. 53). Not only is this body of orthodoxy theoretically inconsistent, it also lacks empirical support. Existing alternatives to this orthodoxy, including Marxian analyses, are much more compelling but while necessary, they are insufficient as a basis for reconstruction.
APA, Harvard, Vancouver, ISO, and other styles
10

Kalmijn, Matthijs. "Family Structure and Father Absence among Immigrant Children: The Role of Migration, Religion and Inequality." In Growing up in Diverse Societies, 143–75. British Academy, 2018. http://dx.doi.org/10.5871/bacad/9780197266373.003.0006.

Full text
Abstract:
This chapter examines differences in the families of ethnic minority and majority youth in four European countries (England, Germany, the Netherlands and Sweden). The focus is on the degree to which the father is absent, as indicated by family structure and the strength of the father–child tie. To explain differences, we use three perspectives: a migration perspective, an economic perspective and a cultural perspective. Considerable heterogeneity is observed: some groups have much higher levels of father absence than the majority (sub-Saharan Africa, the Caribbean and Latin America), whereas others have somewhat lower levels of father absence (Middle East, North Africa, South Asia). Cultural explanations partly explain the lower prevalence of father absence in some groups while suppressing the higher prevalence of father absence in other groups. Economic disadvantage, in contrast, partly explains the higher prevalence of father absence in some groups while suppressing the lower prevalence of father absence in others.
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Diverse explanations"

1

Rodriguez, Pau, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, and David Vazquez. "Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations." In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2021. http://dx.doi.org/10.1109/iccv48922.2021.00109.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Russell, Chris. "Efficient Search for Diverse Coherent Explanations." In FAT* '19: Conference on Fairness, Accountability, and Transparency. New York, NY, USA: ACM, 2019. http://dx.doi.org/10.1145/3287560.3287569.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Artelt, Andre, and Barbara Hammer. "“Even if …” – Diverse Semifactual Explanations of Reject." In 2022 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2022. http://dx.doi.org/10.1109/ssci51031.2022.10022139.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Yuan, Yining, Kevin McAreavey, Shujun Li, and Weiru Liu. "Multi-Granular Evaluation of Diverse Counterfactual Explanations." In 16th International Conference on Agents and Artificial Intelligence. SCITEPRESS - Science and Technology Publications, 2024. http://dx.doi.org/10.5220/0012349900003636.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Mothilal, Ramaravind K., Amit Sharma, and Chenhao Tan. "Explaining machine learning classifiers through diverse counterfactual explanations." In FAT* '20: Conference on Fairness, Accountability, and Transparency. New York, NY, USA: ACM, 2020. http://dx.doi.org/10.1145/3351095.3372850.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Han, Chan Sik, and Keon Myung Lee. "Gradient-based Counterfactual Generation for Sparse and Diverse Counterfactual Explanations." In SAC '23: 38th ACM/SIGAPP Symposium on Applied Computing. New York, NY, USA: ACM, 2023. http://dx.doi.org/10.1145/3555776.3577737.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Vo, Vy, Trung Le, Van Nguyen, He Zhao, Edwin V. Bonilla, Gholamreza Haffari, and Dinh Phung. "Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations." In KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, NY, USA: ACM, 2023. http://dx.doi.org/10.1145/3580305.3599343.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

MacNeil, Stephen, Andrew Tran, Dan Mogil, Seth Bernstein, Erin Ross, and Ziheng Huang. "Generating Diverse Code Explanations using the GPT-3 Large Language Model." In ICER 2022: ACM Conference on International Computing Education Research. New York, NY, USA: ACM, 2022. http://dx.doi.org/10.1145/3501709.3544280.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Artelt, André, and Andreas Gregoriades. "“How to Make Them Stay?”: Diverse Counterfactual Explanations of Employee Attrition." In 25th International Conference on Enterprise Information Systems. SCITEPRESS - Science and Technology Publications, 2023. http://dx.doi.org/10.5220/0011961300003467.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Artelt, André, Alexander Schulz, and Barbara Hammer. ""Why Here and not There?": Diverse Contrasting Explanations of Dimensionality Reduction." In 12th International Conference on Pattern Recognition Applications and Methods. SCITEPRESS - Science and Technology Publications, 2023. http://dx.doi.org/10.5220/0011618300003411.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "Diverse explanations"

1

McGee, Steven, Randi McGee-Tekula, and Jennifer Duck. Does a Focus on Modeling and Explanation of Molecular Interactions Impact Student Learning and Identity? The Learning Partnership, April 2017. http://dx.doi.org/10.51420/conf.2017.1.

Full text
Abstract:
The Interactions curriculum and professional development program is designed to support high school teachers in their transition to the physical science Next Generation Science Standards. Through curriculum materials, an online portal for delivering the digital materials, interactive models of molecular phenomena, and educative teacher guide, teachers are able to support students in bridging the gap between macroscopic and sub-microscopic ideas in physical science by focusing on a modeling and explanation-oriented exploration of attractions and energy changes at the atomic level. During the fall semester of the 2015-16 school year, The Learning Partnership conducted a field test of Interactions with eleven teachers who implemented the curriculum across a diverse set of school districts. As part of the field test, The Learning Partnership examined the impact of teachers’ inquiry-based teaching practices on student learning and identification with the scientific enterprise. The results indicate that students had statistically significant growth in learning from the beginning to end of unit 2 and that the extent to which teachers engaged students in inquiry had a positive statistically significant influence on the growth rate and a statistically significant indirect impact on students’ identification with the scientific enterprise.
APA, Harvard, Vancouver, ISO, and other styles
2

Blundell, S. Tutorial : the DEM Breakline and Differencing Analysis Tool—step-by-step workflows and procedures for effective gridded DEM analysis. Engineer Research and Development Center (U.S.), November 2022. http://dx.doi.org/10.21079/11681/46085.

Full text
Abstract:
The DEM Breakline and Differencing Analysis Tool is the result of a multi-year research effort in the analysis of digital elevation models (DEMs) and the extraction of features associated with breaklines identified on the DEM by numerical analysis. Developed in the ENVI/IDL image processing application, the tool is designed to serve as an aid to research in the investigation of DEMs by taking advantage of local variation in the height. A set of specific workflow exercises is described as applied to a diverse set of four sample DEMs. These workflows instruct the user in applying the tool to extract and analyze features associated with terrain, vegetative canopy, and built structures. Optimal processing parameter choices, subject to user modification, are provided along with sufficient explanation to train the user in elevation model analysis through the creation of customized output overlays.
APA, Harvard, Vancouver, ISO, and other styles
3

Ardanaz, Martín, Evelyne Hübscher, Philip Keefer, and Thomas Sattle. Policy Misperceptions, Information, and the Demand for Redistributive Tax Reform: Experimental Evidence from Latin American Countries. Inter-American Development Bank, December 2022. http://dx.doi.org/10.18235/0004655.

Full text
Abstract:
Why do individuals preferences for redistribution often diverge widely from their material self-interest? Using an original online survey experiment spanning eight countries and 12,000 respondents across Latin America, one of the most unequal regions in the world, we find significant evidence for an under-explored explanation: misconceptions regarding the distributional effects of current tax policy. Treated respondents who are informed that an increase in the value added tax (VAT) is regressive are significantly more likely to prefer policy reforms that make the tax more progressive. Treatment effects are driven by the large fraction of respondents who underestimate the regressivity of the VAT, even though their misperceptions are linked to fundamental views about the world. These respondents are disproportionately right-leaning and more likely to attribute success to individual effort than luck. Despite the deep-rooted nature of respondents misperceptions, treatment effects are largest among individuals who hold these views of the world. These findings contribute both to understanding the political economy of redistribution and the potential for information interventions to shift support for fiscal adjustment policies protecting the most vulnerable.
APA, Harvard, Vancouver, ISO, and other styles
4

Ardanaz, Martín, Evelyne Hübscher, Philip Keefer, and Thomas Sattler. Policy Misperceptions, Information, and the Demand for Redistributive Tax Reform: Experimental evidence from Latin America. Inter-American Development Bank, September 2022. http://dx.doi.org/10.18235/0004473.

Full text
Abstract:
Scholars have long struggled to understand why individual preferences for redistribution often diverge widely from their material self-interest. The puzzle is acute in Latin America, largely democratic and yet one of the most unequal regions in the world. Using an original online survey experiment spanning 8 countries and 12,000 respondents across Latin America, we find significant evidence for an under-explored explanation: misconceptions regarding the distributional effects of current tax policy. Treated respondents who are informed that an increase in the value-added tax (VAT) is regressive are significantly more likely to prefer policy reforms that make the tax more progressive. We are further able to identify mechanisms. A large fraction of respondents underestimate the regressivity of the VAT. Their misperceptions are linked to fundamental views about the world: these respondents are disproportionately right-leaning and more likely to attribute success to individual effort than luck. Despite the deep-rooted nature of their misperceptions, treatment effects are largest among individuals who believe the VAT is not regressive. These findings contribute both to understanding the political economy of redistribution and the potential for information interventions to shift support for fiscal adjustment policies protecting the most vulnerable.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Diverse explanations' for particular source types:
Journal articles Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography