Filters








3,993 Hits in 4.6 sec

A Computational Model of Commonsense Moral Decision Making [article]

Richard Kim, Max Kleiman-Weiner, Andres Abeliuk, Edmond Awad, Sohan Dsouza, Josh Tenenbaum, Iyad Rahwan
2018 arXiv   pre-print
We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics.  ...  ethical decision-making.  ...  This paper makes the following distinct contributions towards building an ethical AI: • Introducing a novel computational model of moral decision making that characterizes moral dilemma as a tradeoff of  ... 
arXiv:1801.04346v1 fatcat:lkakszmxwvejbeptk2m3kxylc4

Interactive Learning and Analogical Chaining for Moral and Commonsense Reasoning

Joseph Blass
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
I propose to develop a model of repeated analogical chaining and analogical reasoning to enable autonomous agents to interactively learn to apply common sense and model an individual's moral norms.  ...  Autonomous systems must consider the moral ramifications of their actions. Moral norms vary among people and depend on common sense, posing a challenge for encoding them explicitly in a system.  ...  MoralDM, SME, and Companions MoralDM (Dehghani et al. 2009) , the basis of my work, is a computer model of moral reasoning that takes in a moral dilemma in natural language, uses a natural language understanding  ... 
doi:10.1609/aaai.v30i1.9817 fatcat:k64lvxfpbvdcdnmfnol5eme3o4

Machine Common Sense [article]

Alexander Gavrilenko, Katerina Morozova
2020 arXiv   pre-print
Algorithms provide tools for a situation analysis, while personal models make it possible to identify personality traits.  ...  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI). There is a wide range of strategies that can be employed to make progress on this challenge.  ...  The point is that where to acquire commonsense knowledge for decision-making in view of human-human interactions?  ... 
arXiv:2006.08409v1 fatcat:wmnbkud4dvdibl4fglnmacsita

A Word on Machine Ethics: A Response to Jiang et al. (2021) [article]

Zeerak Talat, Hagen Blix, Josef Valvoda, Maya Indira Ganesh, Ryan Cotterell, Adina Williams
2021 arXiv   pre-print
In this work, we focus on a single case study of the recently proposed Delphi model and offer a critique of the project's proposed method of automating morality judgments.  ...  One proposal in this vein is the construction of morality models that can take in arbitrary text and output a moral judgment about the situation described.  ...  A full listing of those who helped us in the drafting of this manuscript will be provided in future drafts.  ... 
arXiv:2111.04158v1 fatcat:ewnffpikkralvi7iupseexzotu

Can Machines Learn Morality? The Delphi Experiment [article]

Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny Liang, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jon Borchardt, Saadia Gabriel, Yulia Tsvetkov, Oren Etzioni (+3 others)
2022 arXiv   pre-print
Existing AI systems deployed to millions of users, however, are already making decisions loaded with moral implications, which poses a seemingly impossible challenge: teaching machines moral sense, while  ...  Despite that, we demonstrate positive use cases of imperfect Delphi, including using it as a component model within other imperfect AI systems.  ...  LJ and MS conducted the United Nation Universal Declaration of Human Rights probing analysis with advice from JDH and JL. RLB and LJ collected data annotations for the Delphi+ model.  ... 
arXiv:2110.07574v2 fatcat:rm3vipytkrexhjewrn2bnmve2a

Aligning AI With Shared Human Values [article]

Dan Hendrycks and Collin Burns and Steven Basart and Andrew Critch and Jerry Li and Dawn Song and Jacob Steinhardt
2021 arXiv   pre-print
We show how to assess a language model's knowledge of basic concepts of morality.  ...  We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality.  ...  Eventually work should apply human value models in multimodal and sequential decision making environments (Hausknecht et al., 2019) .  ... 
arXiv:2008.02275v5 fatcat:dcq5jt2nibgedajzxsibnpf2xq

To Root Artificial Intelligence Deeply in Basic Science for a New Generation of AI [article]

Jingan Yang, Yang Peng
2020 arXiv   pre-print
), develop a new inference engine for cognitive network recognition~(CNR); (v)~to develop high-precision, multi-modal intelligent perceptrons; (vi)~investigating intelligent reasoning and fast decision-making  ...  (iii)~to root brain-computer interface~(BCI) and brain-muscle interface~(BMI) technologies deeply in science on human behaviour; (iv)~making research on knowledge-driven visual commonsense reasoning~(VCR  ...  Current State-of-the-Art of Artificial Intelligence The research progress of artificial intelligence is tortuous, that is, there are climaxes and troughs. The first trough of AI research: 1974-1980.  ... 
arXiv:2009.05678v1 fatcat:vn4pdl3k7jdwrmx4dygsyyfxvy

Consciousness and Commonsense Critics in Cognitive Architectures

K. R. Shylaja, Vijayakumar Maragal Venkatamuni, Darryl N. Davis, E. V. Prasad
2012 International Journal of Artificial Life Research  
A six tiered (layers) SMCA control model is designed that relies on a society of agents operating using metrics associated with the principles of artificial economics in animal cognition.  ...  The research identifies the concepts of consciousness and commonsense.  ...  COGNITIVE THEORY OF CONSCIOUSNESS Cognitive science provides theories for designing computational models of mind.  ... 
doi:10.4018/jalr.2012040103 fatcat:2fdlb2k5grafbdxp3ifmyqemka

Page 880 of Psychological Abstracts Vol. 83, Issue 2 [page]

1996 Psychological Abstracts  
—Presents a model of how expert defensive system operators (DSOs) on a Bl bomber examine a complex series of signals, categorize whether those signals are dangerous or not, and then make a decision on  ...  Computer simulation shows that this agent can effectively reach the goal in a maze-like environment. The relation of this model to the human brain is discussed.  ... 

SENTIMENTALIST PLURALISM: MORAL PSYCHOLOGY AND PHILOSOPHICAL ETHICS*

Michael B. Gill, Shaun Nichols
2008 Philosophical Issues  
holds that commonsense moral judgment is guided by a plurality of moral rules, 2 and [3] prescriptive moral pluralism, which holds that moral judgment ought to be guided by a plurality of moral rules.  ...  When making moral judgments, people are typically guided by a plurality of moral rules. These rules owe their existence to human emotions but are not simply equivalent to those emotions.  ...  While Fodor's law might be somewhat hyperbolic, it is clear that we are nowhere near having detailed processing models of the kind of global decision making that is implicated in difficult moral decisionmaking  ... 
doi:10.1111/j.1533-6077.2008.00142.x fatcat:fii2fqtuwva5paz733dgxqwkte

The Naïve Utility Calculus: Computational Principles Underlying Commonsense Psychology

Julian Jara-Ettinger, Hyowon Gweon, Laura E. Schulz, Joshua B. Tenenbaum
2016 Trends in Cognitive Sciences  
We propose that human social cognition is structured around a basic understanding of ourselves and others as intuitive utility maximizers: From a young age, humans implicitly assume that agents choose  ...  We review studies providing support for the naïve utility calculus, and we show how it captures much of the rich social reasoning humans engage in from infancy.  ...  This intuitive decision-theory is therefore, by definition, a cornerstone of any scientific theory of human decision making.  ... 
doi:10.1016/j.tics.2016.05.011 pmid:27388875 fatcat:l4j62lpxjzg2hmabaqvth6plbm

The Naïve Utility Calculus: Computational Principles Underlying Commonsense Psychology

Julian Jara-Ettinger, Hyowon Gweon, Laura E. Schulz, Joshua B. Tenenbaum
2016 Trends in Cognitive Sciences  
We propose that human social cognition is structured around a basic understanding of ourselves and others as intuitive utility maximizers: From a young age, humans implicitly assume that agents choose  ...  We review studies providing support for the naïve utility calculus, and we show how it captures much of the rich social reasoning humans engage in from infancy.  ...  This intuitive decision-theory is therefore, by definition, a cornerstone of any scientific theory of human decision making.  ... 
doi:10.1016/j.tics.2016.08.007 pmid:27612984 fatcat:orxyxs42sbastaa7al7hwpwbpi

Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence [article]

Mark O. Riedl
2016 arXiv   pre-print
We argue that instilling artificial intelligences with computational narrative intelligence affords a number of applications beneficial to humans.  ...  Finally, we argue that computational narrative is a practical step towards machine enculturation, the teaching of sociocultural values to machines.  ...  The AI makes decisions that sometimes can be hard for us to make sense of. Their failures are often due to the fact that they cannot make sense of what we are trying to accomplish or why.  ... 
arXiv:1602.06484v1 fatcat:xf23w6rkzvddlmc6evy7mp3bdy

Personality Assessment from Text for Machine Commonsense Reasoning [article]

Niloofar Hezarjaribi, Zhila Esna Ashari, James F. Frenzel, Hassan Ghasemzadeh, Saied Hemati
2020 arXiv   pre-print
Our analysis of data collected with 300 participants demonstrate that PerSense predicts answers to commonsense questions with 82.3% accuracy using a Random Forest classifier.  ...  To assess the feasibility of commonsense reasoning analysis, we train ML algorithms to predict responses to commonsense questions.  ...  A driver-less car should be equipped with commonsense reasoning for simply maximizing the gain and minimizing the loss in its decision making process.  ... 
arXiv:2004.09275v1 fatcat:igzc6jq7tnedhcdutozebr2kxa

Learning a commonsense moral theory

Max Kleiman-Weiner, Rebecca Saxe, Joshua B. Tenenbaum
2017 Cognition  
Our model explains how children can build from sparse noisy observations of how a small set of individuals make moral decisions to a broad moral competence, able to support an infinite range of judgments  ...  Learning a commonsense moral theory. Cognition (2017), http://dx.  ...  MKW was supported by a Hertz Foundation Fellowship and NSF-GRFP. JBT was funded by NSF STC award CCF-1231216 and by an ONR grant N00014-13-1-0333.  ... 
doi:10.1016/j.cognition.2017.03.005 pmid:28351662 fatcat:ep4vxgytfzfonalobmqvwilevi
« Previous Showing results 1 — 15 out of 3,993 results