Human-like Communication

2021 ◽  
pp. 137-151
Author(s):  
Patrick G. T. Healey
Keyword(s):  
Machine Intelligence ◽  
Human Interaction ◽  
Grand Challenge ◽  
Human Communication ◽  
Fine Grained ◽  
Current State ◽  
Shared Language ◽  
Everyday Interaction ◽  
Ordinary Conversation ◽  
New Situation

The most famous grand challenge for machine intelligence is human-like communication. This chapter explores two problem that need to be solved in order for machines to meet this challenge. The first is the technical difficulties posed by ordinary conversation. Production and comprehension in conversation are: multimodal, multi-person, incremental, concurrent, and jointly managed. The fine-grained complexity of these aspects of human interaction are beyond the current state of the art but should, ultimately, be tractable. The second set of problems are foundational. Models that assume human communication is underwritten by a shared language are unable to account for the ubiuquitous and systematic role misunderstanding plays in everyday interaction. As a result they also fail to explain how people adapt their language use to each new person and new situation in real time. This capability is essential for any machine that aims to engage constructively with human diversity.

Behavioral Genetics: Concepts for Research and Practice in Language Development and Disorders

1995 ◽  
Vol 38 (5) ◽  
pp. 1126-1142 ◽  
Author(s):  
Jeffrey W. Gilger
Keyword(s):  
Language Development ◽  
Behavioral Genetics ◽  
State Of The Art ◽  
Genetic Research ◽  
Great Promise ◽  
Behavioral Genetic ◽  
Fine Grained ◽  
Future Goals ◽  
Current State ◽  
Research Designs

This paper is an introduction to behavioral genetics for researchers and practioners in language development and disorders. The specific aims are to illustrate some essential concepts and to show how behavioral genetic research can be applied to the language sciences. Past genetic research on language-related traits has tended to focus on simple etiology (i.e., the heritability or familiality of language skills). The current state of the art, however, suggests that great promise lies in addressing more complex questions through behavioral genetic paradigms. In terms of future goals it is suggested that: (a) more behavioral genetic work of all types should be done—including replications and expansions of preliminary studies already in print; (b) work should focus on fine-grained, theory-based phenotypes with research designs that can address complex questions in language development; and (c) work in this area should utilize a variety of samples and methods (e.g., twin and family samples, heritability and segregation analyses, linkage and association tests, etc.).

scholarly journals Representation Learning for Fine-Grained Change Detection

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4486
Author(s):  
Niall O’Mahony ◽  
Sean Campbell ◽  
Lenka Krpalkova ◽  
Anderson Carvalho ◽  
Joseph Walsh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Model Calibration ◽  
State Of The Art ◽  
Representation Learning ◽  
Machine Intelligence ◽  
The State ◽  
Sensor Data ◽  
Fine Grained ◽  
Learning Techniques

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.

The Role of Constraints and Human Interaction in Evolving MEMS Designs: Microresonator Case Study

2004 ◽  
Author(s):  
Raffi Kamalian ◽  
Alice M. Agogino ◽  
Hideyuki Takagi
Keyword(s):  
Genetic Algorithms ◽  
Geometric Constraints ◽  
Human Interaction ◽  
Design System ◽  
Current State ◽  
Mems Resonator ◽  
Computer Aided ◽  
Generative Methods

In this paper we review the current state of automated MEMS synthesis with a focus on generative methods. We use the design of a MEMS resonator as a case study and explore the role that geometric constraints and human interaction play in a computer-aided MEMS design system based on genetic algorithms.

scholarly journals Inferring object properties from human interaction and transferring them to new motions

2021 ◽  
Author(s):  
Qian Zheng ◽  
Weikai Wu ◽  
Hanting Pan ◽  
Niloy Mitra ◽  
Daniel Cohen-Or ◽  
...  
Keyword(s):  
Human Interaction ◽  
Strongly Correlated ◽  
Recognition Method ◽  
Fine Grained ◽  
Object Property ◽  
Correlated Motions ◽  
Object Properties ◽  
New Synthesis ◽  
Related Object ◽  
Highly Correlated

AbstractHumans regularly interact with their surrounding objects. Such interactions often result in strongly correlated motions between humans and the interacting objects. We thus ask: “Is it possible to infer object properties from skeletal motion alone, even without seeing the interacting object itself?” In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone. This inference allows us to disentangle the motion from the object property and transfer object properties to a given motion. We collected a large number of videos and 3D skeletal motions of performing actors using an inertial motion capture device. We analyzed similar actions and learned subtle differences between them to reveal latent properties of the interacting objects. In particular, we learned to identify the interacting object, by estimating its weight, or its spillability. Our results clearly demonstrate that motions and interacting objects are highly correlated and that related object latent properties can be inferred from 3D skeleton sequences alone, leading to new synthesis possibilities for motions involving human interaction. Our dataset is available at http://vcc.szu.edu.cn/research/2020/IT.html.

scholarly journals The Application of Affective Computing Technology to E-Learning

2014 ◽  
pp. 109-128
Author(s):  
Nik Thompson ◽  
Tanya Jane McGill
Keyword(s):  
Affective Computing ◽  
Physiological State ◽  
Affective State ◽  
Significant Proportion ◽  
Human Interaction ◽  
Human Communication ◽  
Tutoring Systems ◽  
User Input ◽  
E Learning ◽  
New Generation

This chapter discusses the domain of affective computing and reviews the area of affective tutoring systems: e-learning applications that possess the ability to detect and appropriately respond to the affective state of the learner. A significant proportion of human communication is non-verbal or implicit, and the communication of affective state provides valuable context and insights. Computers are for all intents and purposes blind to this form of communication, creating what has been described as an “affective gap.” Affective computing aims to eliminate this gap and to foster the development of a new generation of computer interfaces that emulate a more natural human-human interaction paradigm. The domain of learning is considered to be of particular note due to the complex interplay between emotions and learning. This is discussed in this chapter along with the need for new theories of learning that incorporate affect. Next, the more commonly applicable means for inferring affective state are identified and discussed. These can be broadly categorized into methods that involve the user’s input and methods that acquire the information independent of any user input. This latter category is of interest as these approaches have the potential for more natural and unobtrusive implementation, and it includes techniques such as analysis of vocal patterns, facial expressions, and physiological state. The chapter concludes with a review of prominent affective tutoring systems in current research and promotes future directions for e-learning that capitalize on the strengths of affective computing.

scholarly journals How Communication Scholars See Open Scholarship: A survey of International Communication Association scholars

2021 ◽  
Author(s):  
Nicholas David Bowman ◽  
Eike Mark Rinke ◽  
Eun-Ju Lee ◽  
Robin Nabi ◽  
Claes de Vreese
Keyword(s):  
International Communication ◽  
Human Communication ◽  
Future Directions ◽  
Current State

A growing number of communication scholars have pushed for increased accountability and transparency in scholarship. While perspectives on open scholarship practices (OSPs) are noted in editorials and positions papers, we lack insights into how the larger community understands, feels about, engages with, and supports OSPs in practice. A mixed-methodological survey of International Communication Association members (N = 330) reported broad familiarity with and support for some OSPs, but less engagement with them. Respondents shared several concerns, including reservations about unclear standards, presumed incompatibility with some scholarly approaches, misuse of shared materials, and aggression from others. The reported findings inform debates around the current state and future directions of openness and transparency in the study of human communication.

Ontology-Driven Creation of Contents

2012 ◽  
pp. 156-170
Author(s):  
Kambiz Badie ◽  
Mahmood Kharrat ◽  
Maryam Tayefeh Mahmoudi ◽  
Maryam S. Mirian ◽  
Tahereh M. Ghazi ◽  
...  
Keyword(s):  
Human Interaction ◽  
Education Development ◽  
Problem Context ◽  
Agent Based ◽  
New Situation

In this chapter, a framework is discussed for creating contents to help significant organizational tasks such as planning, research, innovation, education, development, et cetera be achieved in an efficient way. The proposed framework is based on an interplay between the ontologies of the key segments and the problem context using the linguistically significant notions for each key segment. Once a certain organizational task is faced these notions are adjusted to create a new content filling the new situation. In the chapter, an agent-based architecture is discussed to show how human interaction with his/her surrounding organization can be realized through using this framework.

scholarly journals What’s in a Bantu verb? Actionality in Bantu languages

2019 ◽  
Vol 23 (2) ◽  
pp. 303-345 ◽  
Author(s):  
Thera Marie Crane ◽  
Bastian Persohn
Keyword(s):  
Real World ◽  
Future Research ◽  
State Change ◽  
Bantu Languages ◽  
Fine Grained ◽  
Current State ◽  
Quality Evidence

Abstract The lexical and phrasal dimensions of aspect and their interactions with morphosyntactic aspectual operators have proved difficult to model in Bantu languages. Bantu actional types do not map neatly onto commonly accepted categorizations of actionality, although these are frequently assumed to be universal and based on real-world event typologies. In this paper, we describe important characteristics and major actional distinctions attested across Bantu languages. These, we argue, include complex lexicalizations consisting of a coming-to-be phase, the ensuing state change, and the resultant state; sub-distinctions of coming-to-be phases, and other issues of phasal quality. Despite these fine-grained distinctions in phasal structure and quality, evidence for a principled distinction between activity- and accomplishment-like predicates is mixed. We review the current state of evidence for these characteristics of Bantu actionality and sketch methodological directions for future research.

Predictive Models in Urology

2013 ◽  
Vol 80 (1) ◽  
pp. 42-45 ◽  
Author(s):  
Andrea Cestari
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Predictive Modeling ◽  
Predictive Models ◽  
Machine Intelligence ◽  
Health Records ◽  
Knowledge Based ◽  
Current State ◽  
Computer Based ◽  
Future Direction

Predictive modeling is emerging as an important knowledge-based technology in healthcare. The interest in the use of predictive modeling reflects advances on different fronts such as the availability of health information from increasingly complex databases and electronic health records, a better understanding of causal or statistical predictors of health, disease processes and multifactorial models of ill-health and developments in nonlinear computer models using artificial intelligence or neural networks. These new computer-based forms of modeling are increasingly able to establish technical credibility in clinical contexts. The current state of knowledge is still quite young in understanding the likely future direction of how this so-called ‘machine intelligence’ will evolve and therefore how current relatively sophisticated predictive models will evolve in response to improvements in technology, which is advancing along a wide front. Predictive models in urology are gaining progressive popularity not only for academic and scientific purposes but also into the clinical practice with the introduction of several nomograms dealing with the main fields of onco-urology.

scholarly journals Evaluation of Commonly Used Algorithms for Thyroid Ultrasound Images Segmentation and Improvement Using Machine Learning Approaches

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Prabal Poudel ◽  
Alfredo Illanes ◽  
Debdoot Sheet ◽  
Michael Friebe
Keyword(s):  
Machine Learning ◽  
Active Contours ◽  
Computation Time ◽  
Machine Intelligence ◽  
Ease Of Use ◽  
Human Interaction ◽  
Ultrasound Images ◽  
Learning Approaches ◽  
Thyroid State ◽  
Advantages And Disadvantages

The thyroid is one of the largest endocrine glands in the human body, which is involved in several body mechanisms like controlling protein synthesis and the body's sensitivity to other hormones and use of energy sources. Hence, it is of prime importance to track the shape and size of thyroid over time in order to evaluate its state. Thyroid segmentation and volume computation are important tools that can be used for thyroid state tracking assessment. Most of the proposed approaches are not automatic and require long time to correctly segment the thyroid. In this work, we compare three different nonautomatic segmentation algorithms (i.e., active contours without edges, graph cut, and pixel-based classifier) in freehand three-dimensional ultrasound imaging in terms of accuracy, robustness, ease of use, level of human interaction required, and computation time. We figured out that these methods lack automation and machine intelligence and are not highly accurate. Hence, we implemented two machine learning approaches (i.e., random forest and convolutional neural network) to improve the accuracy of segmentation as well as provide automation. This comparative study intends to discuss and analyse the advantages and disadvantages of different algorithms. In the last step, the volume of the thyroid is computed using the segmentation results, and the performance analysis of all the algorithms is carried out by comparing the segmentation results with the ground truth.

Sign in / Sign up

Export Citation Format

Share Document