145,537 Hits in 8.5 sec

Learning and Inference for Structured Prediction: A Unifying Perspective

Aryan Deshwal, Janardhan Rao Doppa, Dan Roth
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In this paper, we present a unifying perspective of the different frameworks that address structured prediction problems and compare them in terms of their strengths and weaknesses.  ...  Prototypical structured prediction tasks include part-of-speech tagging (predicting POS tag sequence for an input sentence) and semantic segmentation of images (predicting semantic labels for pixels of  ...  Acknowledgements This work was supported in part by NSF grants #1910213 and #1845922, and in part by Contracts W911NF15-1-0461 and HR0011-17-S-0048 with the US Defense Advanced Research Projects Agency  ... 
doi:10.24963/ijcai.2019/878 dblp:conf/ijcai/DeshwalDR19 fatcat:lmpr57bvajfqdmafbkdzg4dpi4

Conceptual Modelling and Artificial Intelligence: Overview and research challenges from the perspective of predictive business process management

Peter Fettke
2020 Modellierung  
Currently, the visibility of Artificial Intelligence (AI) and society's expectations of AI are very high, particularly compared to other research topics, namely Modelling.  ...  Predictive process management uses machine learning for predicting the future state of a running process instance. The paper closes with some general remarks and research challenges.  ...  Background Artificial Intelligence The field of AI has a long history and its original foundation is typically dated back to the 1950s [3] .  ... 
dblp:conf/modellierung/Fettke20 fatcat:e2s67dd5qbccbitm5yechlowem

Algorithmic Bias in Recidivism Prediction: A Causal Perspective (Student Abstract)

Aria Khademi, Vasant Honavar
ProPublica's analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were  ...  In the case of FM, odds of the COM-PAS software predicting that African American defendants would recidivate after release is exp(0.624) ≈ 1.87 times that of White defendants.  ...  Our estimates of NNM, NNMPC, MMMPC, and FM were robust to unmeasured confounding up to Γs of 9, 7.5, 8, and 5.5, respectively. We conclude that our FACT estimates are robust to unmeasured confounders.  ... 
doi:10.1609/aaai.v34i10.7192 fatcat:o7bshgthrzgi5mecdwojkafbne

Emotional Intelligence or Artificial Intelligence?: Emotional Artificial Intelligence

Emine Kambur
2015 Florya Chronicles of Political Economy  
The data are collected from 152 people who have knowledge of emotional intelligence and artificial intelligence.  ...  It examines how emotional intelligence affects artificial intelligence and the cause-effect relationship between the two.  ...  METHODOLOGY The purpose of this study is to reveal whether emotional intelligence affects their perspectives towards artificial intelligence.  ... 
doi:10.17932/iau.fcpe.2015.010/fcpe_v07i2004 fatcat:fu3cqulyijecdkzd2bnncrmziy

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction.  ...  In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.  ...  First, we propose the multilevel graph network to directly model the multilevel quantum interactions of molecules from hierarchical perspectives (i.e., atom-wise, pair-wise, triplewise, etc), which developed  ... 
doi:10.1609/aaai.v33i01.33011052 fatcat:zseoxqmawnbflf33i3duogi6qm

Artificial Intelligence for Artificial Artificial Intelligence

Peng Dai, . Mausam, Daniel Weld
Crowdsourcing platforms such as Amazon Mechanical Turk have become popular for a wide variety of human intelligence tasks; however, quality control continues to be a significant challenge.  ...  We validate the model and use it to control a successive-improvement process on Mechanical Turk.  ...  We thank Greg Little and Rob Miller for providing the TurKit code and answering many technical questions.  ... 
doi:10.1609/aaai.v25i1.8096 fatcat:3oz2vkq74vdt7ff5ssd6ahqqee

Artificial intelligence [chapter]

2021 Effective Directors  
Worldwide, artificial intelligence (AI) presents opportunities in a whole variety of sectors: healthcare, education, financial services, marketing, retail, agriculture, energy conservation, government,  ...  Allied with biotechnology and data analytics, it can be used to tackle a huge number of worldwide problems, where the predictive, analytical, and problem-solving nature of AI can make a huge difference  ...  as intelligibility, openness, fairness, and lack of bias, especially as there is a strongly polarised narrative around AI: "the worst or best thing for humanity," according to the late Professor Stephen  ... 
doi:10.4324/9781003201182-64 fatcat:o45gm6zi5zgsze2tnkaqekcj7i

Meta Artificial Intelligence and Artificial Intelligence Director [chapter]

Daiki Satoi, Yuta Mizuno
2019 Encyclopedia of Computer Graphics and Games  
Meta Artificial Intelligence and Artificial Intelligence Director, Fig. 3 An example of enemy spawning by Meta AI.  ...  Cross-References ▶ Character Artificial Intelligence ▶ Navigation Artificial Intelligence  ... 
doi:10.1007/978-3-319-08234-9_309-1 fatcat:7jlhnmeohzgipar376ay77qeri

Artificial Intelligence [article]

John Paul Mueller Luca Massaron
2018 Zenodo  
Artificial Intelligence (AI) has had several false starts and stops over the years, partly because people don't really understand what AI is all about, or even what it should accomplish.  ...  So, the best way to start this book is to define what AI actually is, what it isn't, and how it connects to computers today  ...  It's both a fundamental and challenging task in artificial intelligence.  ... 
doi:10.5281/zenodo.5599660 fatcat:rn6nyx5xinehzpwfy3knurtzgy

Artificial Intelligence [chapter]

Eric Guérin, Orhun Aydin, Ali Mahdavi-Amiri
2019 Manual of Digital Earth  
In this chapter, we provide an overview of different artificial intelligence (AI) and machine learning (ML) techniques and discuss how these techniques have been employed in managing geospatial data sets  ...  We finish the chapter with a discussion of deep learning methods that have high predictive power and have shown great promise in data analysis of geospatial data sets provided by Digital Earth.  ...  Artificial Intelligence Artificial Intelligence  ... 
doi:10.1007/978-981-32-9915-3_10 fatcat:bhm5j3k74naatinb5dpkxag5ky

Intelligence in Artificial Intelligence [article]

Shoumen Palit Austin Datta
2016 arXiv   pre-print
The elusive quest for intelligence in artificial intelligence prompts us to consider that instituting human-level intelligence in systems may be (still) in the realm of utopia.  ...  space and time.  ...  The promise of and the pessimism about AI (artificial intelligence) charts a sinusoidal path. The questions about "intelligence" in AI persists.  ... 
arXiv:1610.07862v2 fatcat:epgbextznvf5fp4qqzveae6cyu

Artificial Intelligence [article]

Denis Rothman
2018 Zenodo  
In May 2017, Google revealed AutoML, an automated machine learning system that could create an artificial intelligence solution without the assistance of a human engineer.  ...  These cloud platforms will slowly but surely reduce the need for artificial intelligence developers. Google Cloud's AI provides intuitive machine learning services.  ...  intelligence Applying artificial intelligence to the blocks of a blockchain to predict and suggest transactions Naive Bayes How to use naive Bayes on blocks of a blockchain to predict further transactions  ... 
doi:10.5281/zenodo.5599649 fatcat:vyqr3zzw5rfzpp3zifezw7uzxq

From Business Intelligence to Artificial Intelligence

Bahman Zohuri
2020 Modern Approaches on Material Science  
With smart malware in modern computation world and necessity for Internet-of-Things (IoT), we are in need of a better intelligence system that today we know it as Artificial Intelligence (AI).  ...  With today's growing information and overloading of its volume based on tremendous size of data growing to the level of big data, Business Intelligence (BI) is not enough to handle any day-to-day business  ...  On the other hand, Artificial Intelligence puts BI in different perspective, knowing that, Artificial Intelligence (AI) is the ability of a computer program or a machine to think and learn similar to the  ... 
doi:10.32474/mams.2020.02.000137 fatcat:jtldl7iy7jdgvia5lc4ff7rbya

Artificial Intelligence Approaches

Yingjie Hu, University at Buffalo, Wenwen Li, Dawn Wright, Orhun Aydin, Daniel Wilson, Omar Maher, Mansour Raad, Arizona State University, Esri, Esri, Esri (+2 others)
2019 Geographic Information Science & Technology Body of Knowledge  
Artificial Intelligence (AI) has received tremendous attention from academia, industry, and the general public in recent years.  ...  We discuss the integration of AI with geography and particularly geographic information science, and present a number of GeoAI applications and possible future directions.  ...  DNN is a special type of artificial neural network which has multiple layers (also called hidden layers) between the input and the output layers.  ... 
doi:10.22224/gistbok/2019.3.4 fatcat:i7wicgaagjefvh5x2dkhtaaxyq

Universal Artificial Intelligence [chapter]

Tom Everitt, Marcus Hutter
2018 Foundations of Trusted Autonomy  
Artificial intelligence (AI) bears the promise of making us all healthier, wealthier, and happier by reducing the need for human labour and by vastly increasing our scientific and technological progress  ...  This chapter will discuss universal artificial intelligence (UAI) as a unifying framework and foundational theory for many (most?) of these approaches.  ...  Background and History of AI Intelligence is a fascinating topic, and has been studied from many different perspectives.  ... 
doi:10.1007/978-3-319-64816-3_2 fatcat:pvbspss75bcftktbrhbyjozyom
« Previous Showing results 1 — 15 out of 145,537 results