scholarly journals That’s Mine! Learning Ownership Relations and Norms for Robots

2019 ◽  
Vol 33 ◽  
pp. 8058-8065 ◽  
Author(s):  
Zhi-Xuan Tan ◽  
Jake Brawer ◽  
Brian Scassellati
Keyword(s):  
Bayesian Inference ◽  
Social Norms ◽  
Recent Work ◽  
Real World ◽  
Autonomous Agents ◽  
Learning Algorithm ◽  
Future Research ◽  
Social Environments ◽  
Social Rules ◽  
Exploratory Stage

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) perceptbased prediction of an object’s likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

scholarly journals Improving Learning-from-Crowds through Expert Validation

2017 ◽  
Author(s):  
Mengchen Liu ◽  
Liu Jiang ◽  
Junlin Liu ◽  
Xiting Wang ◽  
Jun Zhu ◽  
...  
Keyword(s):  
Bayesian Inference ◽  
Supervised Learning ◽  
Real World ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Uncertainty Assessment ◽  
Effective Learning ◽  
Complete Uncertainty ◽  
Expert Validation ◽  
Selection Of

Although several effective learning-from-crowd methods have been developed to infer correct labels from noisy crowdsourced labels, a method for post-processed expert validation is still needed. This paper introduces a semi-supervised learning algorithm that is capable of selecting the most informative instances and maximizing the influence of expert labels. Specifically, we have developed a complete uncertainty assessment to facilitate the selection of the most informative instances. The expert labels are then propagated to similar instances via regularized Bayesian inference. Experiments on both real-world and simulated datasets indicate that given a specific accuracy goal (e.g., 95%) our method reduces expert effort from 39% to 60% compared with the state-of-the-art method.

scholarly journals Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1549
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder ◽  
Aletha B. Carson ◽  
Christian Junge ◽  
David E. Allen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Drinking Behavior ◽  
True Positive Rate ◽  
Training Dataset ◽  
Activity Levels ◽  
Accelerometer Data ◽  
Activity Monitors

Collar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here, we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from more than 5000 videos of more than 2500 dogs and ran the algorithms in production on more than 11 million days of device data. We then surveyed project participants representing 10,550 dogs, which provided 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking (0.772, 0.990), petting (0.305, 0.991), rubbing (0.729, 0.996), scratching (0.870, 0.997), and sniffing (0.610, 0.968). We show that the devices’ position on the collar had no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1514 users), and of 94.9% for drinking (among 1491 users). The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

scholarly journals Transforming Cultural Ideas of Aging and Disability to Improve Policy and Practice

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 645-645
Author(s):  
Anne Ordway
Keyword(s):  
Older Adults ◽  
Health Care ◽  
Recent Work ◽  
Interest Group ◽  
Quality Of Health Care ◽  
Real World ◽  
People With Disabilities ◽  
Policy And Practice ◽  
Full Participation

Abstract Aging and disability are normative processes that extend across the lifespan. However, ageism and ableism are incorporated into many of our practices, programs, and policies—devaluing the lives of older adults and people aging with disabilities and ultimately preventing their full participation in society. Ageism and ableism are closely connected. For example, both systems identify impairment as an individual and social liability. As recent studies have demonstrated, this has real world implications for the quantity and quality of health care requested, delivered, and received by both older adults and people with disabilities. In this session, we discuss the connections between these two forms of oppression and present recent work by researchers in both fields and the FrameWorks Institute that shows how to transform our cultural ideas of aging and disability and development more inclusive policies and services. Part of a symposium sponsored by the Lifelong Disabilities Interest Group.

The pervasive structure of society

2017 ◽  
Vol 44 (8) ◽  
pp. 888-924 ◽  
Author(s):  
Tim Syme
Keyword(s):  
Social Norms ◽  
Social Rules ◽  
Everyday Lives ◽  
Governmental Institutions ◽  
Individual Justice

What does it mean to say that the demands of justice are institutional rather than individual? Justice is often thought to be directly concerned only with governmental institutions rather than individuals’ everyday, legally permissible actions. This approach has been criticized for ignoring the relevance to justice of informal social norms. This paper defends the idea that justice is distinctively institutional but rejects the primacy of governmental institutions. I argue that the ‘pervasive structure of society’ is the site of justice and injustice. It includes all widely enforced social rules and norms, governmental and otherwise, such as informal norms of gender, language and class, and provides a revisionary foundation for the theoretical elucidation and practical pursuit of justice. It provides a framework for evaluating the ways in which people can and should promote justice in their everyday lives.

scholarly journals When Fair Is Not Equal

2017 ◽  
Vol 8 (8) ◽  
pp. 847-857 ◽  
Author(s):  
Kun Zhao ◽  
Eamonn Ferguson ◽  
Luke D. Smillie
Keyword(s):  
Individual Differences ◽  
Social Norms ◽  
Personality Traits ◽  
Big Five ◽  
Real World ◽  
Dictator Game ◽  
Prosocial Behaviors ◽  
Contextual Cues ◽  
Economic Games ◽  
The Real

Growing evidence has highlighted the importance of social norms in promoting prosocial behaviors in economic games. Specifically, individual differences in norm adherence—captured by the politeness aspect of Big Five agreeableness—have been found to predict fair allocations of wealth to one’s partner in the dictator game. Yet, most studies have used neutrally framed paradigms, where players may default to norms of equality in the absence of contextual cues. In this study ( N = 707), we examined prosocial personality traits and dictator allocations under salient real-world norms of equity and need. Extending on the previous research, we found that—in addition to politeness—the compassion aspect of agreeableness predicted greater allocations of wealth when they were embedded in real-world norms. These results represent an important step in understanding the real-world implications of laboratory-based research, demonstrating the importance of both normative context and prosocial traits.

scholarly journals Revisiting the CompCars Dataset for Hierarchical Car Classification: New Annotations, Experiments, and Results

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 596
Author(s):  
Marco Buzzelli ◽  
Luca Segantin
Keyword(s):  
Real World ◽  
High Performance ◽  
Ad Hoc ◽  
Future Research ◽  
Levels Of Detail ◽  
Excellent Starting Point ◽  
Starting Point ◽  
Hierarchical Nature ◽  
Multiple Levels ◽  
Entire Dataset

We address the task of classifying car images at multiple levels of detail, ranging from the top-level car type, down to the specific car make, model, and year. We analyze existing datasets for car classification, and identify the CompCars as an excellent starting point for our task. We show that convolutional neural networks achieve an accuracy above 90% on the finest-level classification task. This high performance, however, is scarcely representative of real-world situations, as it is evaluated on a biased training/test split. In this work, we revisit the CompCars dataset by first defining a new training/test split, which better represents real-world scenarios by setting a more realistic baseline at 61% accuracy on the new test set. We also propagate the existing (but limited) type-level annotation to the entire dataset, and we finally provide a car-tight bounding box for each image, automatically defined through an ad hoc car detector. To evaluate this revisited dataset, we design and implement three different approaches to car classification, two of which exploit the hierarchical nature of car annotations. Our experiments show that higher-level classification in terms of car type positively impacts classification at a finer grain, now reaching 70% accuracy. The achieved performance constitutes a baseline benchmark for future research, and our enriched set of annotations is made available for public download.

Social Norms Sustaining Intimate Partner Violence: A Systematic Review of Methodologies for Proxy Measures

2021 ◽  
pp. 152483802110131
Author(s):  
Ilana Seff
Keyword(s):  
Systematic Review ◽  
Intimate Partner Violence ◽  
Social Norms ◽  
Partner Violence ◽  
Evidence Base ◽  
Intimate Partner ◽  
Future Research ◽  
Data Sets ◽  
Boolean Search ◽  
The Many

In light of the many robust quantitative data sets that include information on attitudes and behaviors related to intimate partner violence (IPV), and in an effort to expand the evidence base around social norms and IPV, many researchers construct proxy measures of norms within and across groups embedded in the data. While this strategy has become increasingly popular, there is no standardized approach for assessing and constructing these norm proxies, and no review of these approaches has been undertaken to date. This study presents the results of a systematic review of methods used to construct quantitative proxy measures for social norms related to IPV. PubMed, Embase, Popline, and Scopus, and PsycINFO were searched using Boolean search techniques. Inclusion criteria comprised studies published since 2000 in English that either (i) examined a norm proxy related to gender or IPV or (ii) analyzed the relationship between a norm proxy and perpetration of, experiences of, or attitudes toward IPV. Studies that employed qualitative methods or that elicited direct measures of descriptive or injunctive norms were not included. Twenty-six studies were eligible for review. Evidence from this review highlights inconsistencies in how proxies are constructed, how they are assessed to ensure valid representation of norms, and how researchers acknowledge their respective method’s limitations. Key processes and reflections employed by some of the studies are identified and recommended for future research inquiries.

scholarly journals Biological Bases of Beauty Revisited: The Effect of Symmetry, Averageness, and Sexual Dimorphism on Female Facial Attractiveness

Symmetry ◽  
2019 ◽  
Vol 11 (2) ◽  
pp. 279 ◽  
Author(s):  
Alex L. Jones ◽  
Bastian Jaeger
Keyword(s):  
Sexual Dimorphism ◽  
Learning Algorithm ◽  
Facial Attractiveness ◽  
Choice Task ◽  
Future Research ◽  
Human Female ◽  
Literature Study ◽  
Skin Texture ◽  
Femininity And Masculinity ◽  
Forced Choice Task

The factors influencing human female facial attractiveness—symmetry, averageness, and sexual dimorphism—have been extensively studied. However, recent studies, using improved methodologies, have called into question their evolutionary utility and links with life history. The current studies use a range of approaches to quantify how important these factors actually are in perceiving attractiveness, through the use of novel statistical analyses and by addressing methodological weaknesses in the literature. Study One examines how manipulations of symmetry, averageness, femininity, and masculinity affect attractiveness using a two-alternative forced choice task, finding that increased masculinity and also femininity decrease attractiveness, compared to unmanipulated faces. Symmetry and averageness yielded a small and large effect, respectively. Study Two utilises a naturalistic ratings paradigm, finding similar effects of averageness and masculinity as Study One but no effects of symmetry and femininity on attractiveness. Study Three applies geometric face measurements of the factors and a random forest machine learning algorithm to predict perceived attractiveness, finding that shape averageness, dimorphism, and skin texture symmetry are useful features capable of relatively accurate predictions, while shape symmetry is uninformative. However, the factors do not explain as much variance in attractiveness as the literature suggests. The implications for future research on attractiveness are discussed.

scholarly journals LANGOS RESPONDS TO SPYROU: CHANGING GROUP NORMS MAY FOSTER POSITIVE RESPONSES TO VICTIMISATION

2015 ◽  
Vol 1 ◽  
Author(s):  
Colette Langos
Keyword(s):  
Social Norms ◽  
Civil Liability ◽  
Bystander Intervention ◽  
Future Research ◽  
Group Norms ◽  
Made In

This article is a comment on Peta Spyrou’s article in this volume entitled ‘Civil Liability for Negligence: An Analysis of Cyberbullying Policies in South Australian Schools’. It highlights some of the original contributions made in the primary article before moving on to consider the importance of changing student norms about cyberbullying and victimisation generally. It identifies themes for future research that aims to change social norms around bystander intervention in instances of bullying and cyberbullying.

Sign in / Sign up

Export Citation Format

Share Document