71,015 Hits in 4.8 sec

Abstraction, Validation, and Generalization for Explainable Artificial Intelligence [article]

Scott Cheng-Hsin Yang, Tomas Folke, Patrick Shafto
2021 arXiv   pre-print
We propose Bayesian Teaching as a framework for unifying explainable AI (XAI) by integrating machine learning and human learning.  ...  Methods to explain AI have been proposed to answer this challenge, but a lack of theory impedes the development of systematic abstractions which are necessary for cumulative knowledge gains.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:2105.07508v2 fatcat:2pok6edf5jbtnapyzj5obayt2e

Page 90 of Library & Information Science Abstracts Vol. , Issue 9 [page]

1995 Library & Information Science Abstracts  
which aims to develop the next generation of generic artificial intelligence tools for military planning, scheduling, and resource allocation and to improve crisis management planning.  ...  which aims to develop the next generation of generic artificial intelligence tools for military planning, scheduling, and resource allocation and to improve crisis management planning.  ... 

Page 67 of Library & Information Science Abstracts Vol. , Issue 8 [page]

1994 Library & Information Science Abstracts  
Artificial Intelligence in Medicine, 6 (2) Apr 94, p.161-73. il.refs. A validation methodology is developed in the domain of diabetes and intended for general use in chronic health management.  ...  Original abstract-amended. (SE) 9408490 Methological issues in validating decision-support systems for insulin dosage adjustment. H. J. Leicester et al.  ... 

Page 1521 of Psychological Abstracts Vol. 62, Issue 6 [page]

1979 Psychological Abstracts  
Results indicate that the use of artificial orthography is not valid when findings are generalized from artificial orthographies to the English alphabet and from various aged individuals to the way young  ...  It is suggested that the uniqueness of this sample does not explain doubts concerning the validity of the accepted standards of the test.  ... 

Explainable Agency in Reinforcement Learning Agents

Prashan Madumal
As humans, we build causal models to encode cause-effect relations of events and use these to explain why events happen.  ...  This thesis explores how reinforcement learning (RL) agents can provide explanations for their actions and behaviours.  ...  regulations for Artificial Intelligence (AI) systems.  ... 
doi:10.1609/aaai.v34i10.7134 fatcat:iv3swpcy4zhzfhloxfsrmc5h2q

Digital Collaborator: Augmenting Task Abstraction in Visualization Design with Artificial Intelligence [article]

Aditeya Pandey, Yixuan Zhang, John A. Guerra-Gomez, Andrea G. Parker, Michelle A. Borkin
2020 arXiv   pre-print
We then propose a conceptual Digital Collaborator: an artificial intelligence system that aims to help visualization practitioners by augmenting their ability to validate and reason about the output of  ...  Under these circumstances, a collaborator can help validate and provide sanity checks to visualization practitioners during this important task abstraction stage.  ...  Introduction Artificial intelligence (AI) has been used in the data information community to help improve design of visualizations [5, 10] .  ... 
arXiv:2003.01304v1 fatcat:hyhdf6l7ebbhdghvfyapyvqdae

Does Artificial Intelligence Have Concept?

Pei Li
2020 Proceedings (MDPI)  
Around these questions, this paper will analyze "concept learning of artificial intelligence" and "concept" respectively, so as to preliminarily answer the question "does artificial intelligence have concept  ...  In recent years, people in the field of artificial intelligence have also begun to study "concept learning" related to "concept". What is "concept learning" in artificial intelligence?  ...  This attempt makes it possible for artificial intelligence to learn the concepts of words.  ... 
doi:10.3390/proceedings47010049 fatcat:du75en56u5dd7bawb6mwqddw5i

Keyphrase Generation for Scientific Articles Using GANs (Student Abstract)

Avinash Swaminathan, Raj Kuwar Gupta, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah
In our GAN model, the generator outputs a sequence of keyphrases based on the title and abstract of a scientific article.  ...  Our model achieves state-of-the-art performance in generation of abstractive keyphrases and is also comparable to the best performing extractive techniques.  ...  Copyright c 2020, Association for the Advancement of Artificial Intelligence (  ... 
doi:10.1609/aaai.v34i10.7238 fatcat:j45hewowpvgj5cqhetgybau7sm

Progressos, reptes i riscos de la Intel·ligència Artificial

Ramon López de Mántaras
2018 Mètode Science Studies Journal: Annual Review  
This text contains some reflections on artificial intelligence (AI). First, I differentiate between strong and weak AI, as well as the concepts related to general and specific AI.  ...  Following this, I briefly describe the main current AI models and discuss the need to provide common-sense knowledge to machines in order to advance towards the goal of a general AI.  ...  ■ ■ DO THE ADVANCES IN SPECIFIC ARTIFICIAL INTELLIGENCE BRING US CLOSER TO GENERAL ARTIFICIAL INTELLIGENCE?  ... 
doi:10.7203/metode.9.11145 fatcat:k4pbivuilvcsff55x2qhmunm6q

Can Machines Design? An Artificial General Intelligence Approach [article]

Andreas Makoto Hein, Hélène Condat
2018 arXiv   pre-print
Recent advances in the field of computational creativity and formal Artificial General Intelligence (AGI) provide frameworks for machines with the general ability to design.  ...  Can they come up with creative solutions to problems and build tools and artifacts across a wide range of domains?  ...  At the same time, the artificial general intelligence community is working on general foundations of intelligence and providing frameworks for formally capturing essential elements of intelligence.  ... 
arXiv:1806.02091v3 fatcat:6et6ydddj5ambp7jyjcwvuqysi

Compression, The Fermi Paradox and Artificial Super-Intelligence [article]

Michael Timothy Bennett
2021 arXiv   pre-print
on symbol emergence and artificial general intelligence.  ...  The following briefly discusses possible difficulties in communication with and control of an AGI (artificial general intelligence), building upon an explanation of The Fermi Paradox and preceding work  ...  Compression, The Fermi Paradox and Artificial Super-Intelligence  ... 
arXiv:2110.01835v1 fatcat:wjq2zz7lbbgnbckktb34p4yzim

A model for parameter setting based on Bayesian networks

Reyes Pavón, Fernando Díaz, Victoria Luzón
2008 Engineering applications of artificial intelligence  
This paper proposes a meta-model that generates the recommendations about the best parameter values for the model of interest.  ...  For evaluation purposes and in order to be able to compare our results with results obtained by others, a real geometric problem was selected.  ...  Pavón et al. / Engineering Applications of Artificial Intelligence 21 (2008) 14-25  ... 
doi:10.1016/j.engappai.2007.02.013 fatcat:uyo5otm5lfbalgmdyfstkulqxy

Applications of Explainable Artificial Intelligence in Diagnosis and Surgery

Yiming Zhang, Ying Weng, Jonathan Lund
2022 Diagnostics  
Some research has been conducted into explainable artificial intelligence (XAI) to overcome the limitation of the black-box nature of AI methods.  ...  In recent years, artificial intelligence (AI) has shown great promise in medicine. However, explainability issues make AI applications in clinical usages difficult.  ...  Hence, in Figure 1 , we show the relationship between artificial intelligence, machine learning, deep learning, and explainable artificial intelligence.  ... 
doi:10.3390/diagnostics12020237 pmid:35204328 pmcid:PMC8870992 fatcat:fk5gbai6szf2vhf222o7p6nkqy

Assessing the Learning of Machine Learning in K-12: A Ten-Year Systematic Mapping

Marcelo Fernando Rauber, Christiane Gresse von Wangenheim
2022 Informatics in Education. An International Journal  
Thus, in order to help students to understand ML, its potential, and limitations and to empower them to become creators of intelligent solutions, diverse courses for teaching ML in K-12 have emerged.  ...  These results indicate a need for more rigorous and comprehensive research in this area.  ...  Acknowledgments This work was supported by the CNPq (National Council for Scientific and Technological Development), a Brazilian government entity focused on scientific and technological development [Grant  ... 
doi:10.15388/infedu.2023.11 fatcat:dm6zy42usbez5fk7a26ykojhsm

Auto articles: an experiment in AI-generated content

Catherine Armitage, Markus Kaindl
2020 Nature  
index MARKUS KAINDL/VOSVIEWER S138 | Nature | Vol 588 | 10 December 2020 Artificial intelligence © 2 0 2 0 S p r i n g e r N a t u r e L i m i t e d . A l l r i g h t s r e s e r v e d .  ...  In this context, artificial intelligence and generative models have been used for molecular de novo design and compound optimization.  ...  De novo generation of hit-like molecules from gene expression signatures using artificial intelligence. Nature Commun. 11, 10 (2020).  ... 
doi:10.1038/d41586-020-03416-9 pmid:33299221 fatcat:b6n24nykmrf6jgb43npyufvgmq
« Previous Showing results 1 — 15 out of 71,015 results