人工智能 | 会议/SCI期刊 约稿信息7条

人工智能

International Journal of Approximate Reasoning

Special Issue on "Defeasible and Ampliative Reasoning"

全文截稿: 2018-02-15

影响因子: 2.845

CCF分类: B类

中科院JCR分区:

  • 大类 : 工程技术 - 2区

  • 小类 : 计算机：人工智能 - 2区

网址: http://www.journals.elsevier.com/international-journal-of-approximate-reasoning/

Classical reasoning is not flexible enough when directly applied to the formalisation of certain nuances of decision making as done by humans. These involve different kinds of reasoning such as reasoning with uncertainty, exceptions, similarity, vagueness, incomplete or contradictory information and many others.

It turns out that everyday reasoning usually shows the two salient intertwined aspects below:

* Ampliative aspect: augmenting the underlying reasoning by allowing more conclusions. In practical contexts, this amounts to the ability to make inferences that venture beyond the scope of the premises, somehow in an unsound but justifiable way. Prominent examples are (i) default reasoning: jumping to conclusions deemed as plausible 'by default', i.e., in the absence of information to the contrary, like applying negation as failure or adopting the closed-world assumption; (ii) inductive and abductive reasoning: taking chances in drawing conclusions that implicitly call for further scrutiny or tests by empirical observations, like in making inductive hypotheses in scientific theories or finding abductive explanations in forensics, and (iii) analogical reasoning: extrapolating from very few examples (in the worst case only one) on the basis of observable similarities or dissimilarities.

* Defeasible aspect: curtailing the underlying reasoning by either disregarding or disallowing some conclusions that somehow ought not to be sanctioned. In practice, this amounts to the ability to backtrack one's conclusions or to admit exceptions in reasoning. Some examples of this are (i) retractive reasoning: withdrawing conclusions that have already been derived, like in belief contraction or in negotiation, and (ii) preemptive reasoning: preventing or blocking the inference of some conclusions by disallowing their derivation in the first place, like in dealing with exceptional cases in multiple inheritance networks and in regulatory systems.

Several efforts have been put into the study and definition of formalisms within which the aforementioned aspects of everyday reasoning could adequately be captured at different levels. Despite the progress that has been achieved, a large avenue remains open for exploration. Indeed, the literature on non-monotonic reasoning has focused almost exclusively on defeasibility of argument forms, whereas belief revision paradigms are restricted to an underlying classical (Tarskian) consequence relation. Moreover, even if some of the issues related to uncertainty in reasoning have been studied using probabilistic approaches and statistical methods, their integration with qualitative frameworks remain a challenge. Finally, well-established approaches are largely based on propositional languages (poor expressiveness) or haunted by the undecidability of full first-order logic. Modern applications require formalisms with a good balance between expressive power and computational complexity in order to be also considered as good candidates for eXplainable Artificial Intelligence (XAI).

This special issue aims at bringing together work on defeasible and ampliative reasoning from the perspective of artificial intelligence, cognitive sciences, philosophy and related disciplines in a multi-disciplinary way, thereby consolidating the mission of the DARe workshop series.

Submissions are welcome on topics relevant to defeasible and ampliative reasoning and that include but are not limited to:

- Abductive and inductive reasoning
- Explanation finding, diagnosis and causal reasoning
- Inconsistency handling and exception-tolerant reasoning
- Decision-making under uncertainty and incomplete information
- Default reasoning, non-monotonic reasoning, non-monotonic logics, conditional logics
- Specific instances and variations of ampliative and defeasible reasoning
- Probabilistic and statistical approaches to reasoning
- Vagueness, rough sets, granularity and fuzzy-logics
- Philosophical foundations of defeasibility
- Empirical studies of reasoning
- Relationship with cognition and language
- Contextual reasoning
- Preference-based reasoning
- Analogical reasoning
- Similarity-based reasoning
- Belief dynamics and merging
- Argumentation theory, negotiation and conflict resolution
- Heuristic and approximate reasoning
- Defeasible normative systems
- Reasoning about actions and change
- Reasoning about knowledge and belief, epistemic and doxastic logics
- Ampliative and defeasible temporal and spatial reasoning
- Computational aspects of reasoning with uncertainty
- Implementations and systems
- Applications of uncertainty in reasoning

人工智能

International Journal of Approximate Reasoning

Special Issue on Uncertainty in Granular Computing

全文截稿: 2018-03-15

影响因子: 2.845

CCF分类: B类

中科院JCR分区:

  • 大类 : 工程技术 - 2区

  • 小类 : 计算机：人工智能 - 2区

网址: http://www.journals.elsevier.com/international-journal-of-approximate-reasoning/

In the real world, uncertainty is a fundamental and unavoidable feature in daily life. In order to deal with uncertainty intelligently, we need to be able to represent it and reason about it. With the popularity of big data and deep learning, uncertainty reasoning meets its new challenges. Extensive research efforts have been dedicated to applying the uncertainty reasoning to practical problems. Granular computing (GrC) is an emerging computing paradigm of information processing, which encourages an approach that recognizes and exploits the knowledge present in data at various levels of resolution or scales. It provides flexibility and adaptability in the resolution at which knowledge or information is extracted and represented. This special issue will target the most recent theoretical and technical progresses on uncertainty reasoning in Granular Computing, such as granular computing theory, three-way decisions, rough sets, classification and clustering etc. This special issue also targets on combining traditional uncertainty reasoning with pratical applications, such as image recognition，video understanding and NLP. The primary objective of this special issue fosters focused attention on the latest research progress in this interesting area.

The special issue seeks for the original contribution of work which addresses the challenges from the uncertainty in Granular Computing. The list of possible topics includes, but not limited to:

Theory and Methodology:

- Uncertainty represention in Granular Computing

- Uncertainty meausre in Granular Computing

- Decision rules and decision making

- Uncertainty in Granular Computing Theory

- Uncertainty in D-S evidence theory

- Uncertainty in Rough Sets

- Uncertainty in Three-way Decisions

- Uncertainty in deep learning

Application:

- Pattern recognition

- Person re-identification

- Image processing and video understanding

- Natural language understanding

- Sentiment Analysis and Opinion Mining

人工智能

Cognitive Systems Research

Special Issue on Crossmodal Learning

全文截稿: 2018-03-19

影响因子: 1.182

中科院JCR分区:

  • 大类 : 工程技术 - 4区

  • 小类 : 计算机：人工智能 - 4区

  • 小类 : 神经科学 - 4区

网址: http://www.journals.elsevier.com/cognitive-systems-research/

I. Aim and Scope

The ability of processing crossmodal information is a fundamental feature of the brain that provides a robust perceptual experience for an efficient interaction with the environment. Consequently, the integration of multisensory information plays a crucial role in autonomous systems to create robust and meaningful representations of objects and events.

For dealing with real-world information, an autonomous, intelligent system must be capable of processing, integrating, and segregating different modalities for the purpose of coherent perception, decision-making, and cognitive learning.

Recent neurophysiological findings in crossmodal learning have inspired novel computational models with the aim to trigger biologically inspired behavioral responses. A rich set of neural mechanisms support the integration and segregation of multimodal stimuli, providing the means to efficiently solve conflicts across modalities.

This special issue aims to invite contributors from psychology, computational neuroscience, artificial intelligence, and cognitive robotics to discuss current research on crossmodal learning mechanisms both from the theoretical and modelling perspective.

II. Potential Topics

Topics include, but are not limited to:

- New theories and findings on crossmodal processing

- New neuroscientific results on crossmodal learning

- Machine learning and neural networks for learning multisensory representations

- Computational models of crossmodal attention and perception

- Brain-inspired approaches for multisensory integration

- Multisensory robot perception

人工智能

Cognitive Systems Research

Special Issue on Social Cognitive Systems in Smart Environments: Approaches for Learning, Reasoning, and Adaptation

全文截稿: 2018-04-30

影响因子: 1.182

中科院JCR分区:

  • 大类 : 工程技术 - 4区

  • 小类 : 计算机：人工智能 - 4区

  • 小类 : 神经科学 - 4区

网址: http://www.journals.elsevier.com/cognitive-systems-research/

I. Aim and Scope

A “smart” environment incorporates intelligent systems (e.g., smart home, smart factory, smart city, smart car etc.) employing heterogeneous devices, such as: sensors, actuators, cameras, networks, and screens. Within such a smart environment, autonomous agents can take on an important mediating role between human users and the environment. This is particularly true if high-level cognitive functions and computational intelligence are employed to handle the uncertainty of the complex environment so as to allow agents to act appropriately within different contexts of interaction.

Using robotic systems in smart environments opens the door to several socio-cognitive applications, such as: reducing cognitive load for individuals interacting with a smart environment, assisting the elderly and people with cognitive disabilities in mobility and daily tasks (which requires robots to learn the multimodal characteristics of human behavior and to spatially perceive the environment containing other smart objects to decide the best way to employ/manipulate them in order to successfully perform tasks), and developing a cloud-connected robot system to incrementally share knowledge between robots in different smart environments about the behavioral characteristics of human users in order to interact with them adaptively. To meet the requirements of these target applications, robots need to be able to learn how to use the capabilities of their smart environments to better address the needs of the human users. Industrial applications of such technologies include factories of the future and the digital eco-system within an autonomous car.

This special issue aims to shed light on cutting-edge lines of interdisciplinary research in cognitive science, artificial intelligence, and robotics covering basic research and applications. Recent advances and possible future research avenues on smart robots and environments would be discussed in detail in this journal special issue.

II. Potential Topics  

Topics relevant to this special issue include, but are not limited to:  

- Cyber-physical systems in smart environments

- Multimodal human robot interaction

- Cognitive modeling of human behavior

- Cognitive architectures and strategies for intelligent interaction with the environment

- AI and machine learning approaches applied to human-robot-environment interaction

- Internet of things

- Ambient assisted living

- Infotainment in smart vehicles

- Natural user interface design

- Cloud robotics

- Ubiquitous computing

人工智能

Pattern Recognition Letters

Special Issue on "AVC-MAA: Advances in Visual Correspondence: Models, Algorithms and Applications"

全文截稿: 2018-05-31

影响因子: 1.995

CCF分类: C类

中科院JCR分区:

  • 大类 : 工程技术 - 3区

  • 小类 : 计算机：人工智能 - 4区

网址: http://www.journals.elsevier.com/pattern-recognition-letters/

Visual correspondence is a key problem in many computer vision and pattern recognition tasks. The past decades have witnessed the rapid expansion of the frontier for automatic correspondence establishment among images/graphics, which is largely due to the advances in computational capacity, data availability and new algorithmic paradigms. Although the visual correspondence problem has been extensively studied in the context of multi-view geometry, its more generalized forms, along with underlying connections among different methods and settings, have not been fully explored. Meanwhile, the combination of big visual data and the deep learning paradigm has achieved significant success in many perceptual tasks; however, the existing paradigm is still far from a panacea to the correspondence problem, which often calls for more careful treatments on the local and global structures. In this special issue, we attempt to assemble recent advances in the correspondence problem, considering the explosions of big visual data applications and the deep learning algorithms.

This special issue will feature original research papers related to the models and algorithms for robust establishment of correspondence, together with applications to real-world problems. The main topics of interest (but are not limited to):

-- Graph matching and image registration: 1) Graph representation and modeling by using image/ graphics data; 2) Robust matching/registration theory and approaches for establishing visual correspondences over two or more images/graphics; 3) Partial, one-to-many or many-to-many matching models and algorithms, especially with major noise and outliers; 4) Similarity between graphs/graphics and graph clustering/classification. 5) Cross-network matching.

-- Tracking and optical flow: 1) Multiple object tracking and association; 2) Robust and/or efficient optical flow methods; 3) Visual trajectory analytics; 4) Person Re-ID.

-- Correspondence for 3-D vision: 1) Calibration, pose estimation and visual SLAM; 2) Depth estimation and 3-D reconstruction.

-- Learning for/by matching: 1) Learning graph structure and similarity from data with established or unestablished correspondences; 2) Learning image feature representation from established or loosely established correspondence; 3) Common/similar objects discovery and recognition from images.

-- Applications: Application of correspondence technology to solve any real-world image understanding problems including object detection/recognition among images/graphics, image stitching, 2-D/3-D recovery, robot vision, photogrammetry and remote sensing, industrial imaging, embed system etc.

人工智能

ai4i 2018

IEEE International Conference on Artificial Intelligence for Industries

全文截稿: 2018-06-17

开会时间: 2018-09-26

会议难度: ★★

CCF分类: 无

会议地点: Laguna Hills, California, USA

网址：http://www.ai4i.org

Artificial Intelligence (AI) is concerned with computing technologies that allow machines to see, hear, talk, think, learn, and solve problems. The huge potential of applying AI for general and domain specific problem solving represents an exciting future that business objectives can be achieved much more effectively. In addition, business-business, business-customer, and customer-customer may be interconnected in a revolutionary way to stimulate tremendous amount of interesting activities.  

The first International Conference on Artificial Intelligence for Industries (ai4i 2018), technically sponsored by IEEE, is an international forum focusing on incorporating artificial intelligence into business products and services that may be brought to the market in the near future. Topics of interest include, but are not limited to, the following:
-Semantic and cognitive aspects in different industries
-Innovative operations using artificial intelligence
-Immersive environments for e-commerce
-Multimodal interaction
-Human/agent interaction
-Business knowledge representation and domain specific problem solving
-Machine and deep learning
-Behaviour and activity generation
-Data generation and validation
-Dialogue modeling and generation
-Data fusion and representation
-System components of intelligent platforms for industries
-New business opportunities

The conference proceedings will be submitted for inclusion to the IEEE Computer Society Press. Distinguished quality papers presented at the conference will be selected for publication in internationally renowned journals.

人工智能

AIAIM 2019

China-Qatar International Workshop on Artificial Intelligence and Applications to Intelligent Manufacturing

全文截稿: 2018-09-15

开会时间: 2019-01-01

会议难度: ★

CCF分类: 无

会议地点: Doha, Qatar

网址：http://aiaim2019.org/

It is our pleasure to welcome you to the 2019 China-Qatar International Workshop on Artificial Intelligence and Applications to Intelligent Manufacturing (AIAIM2019) which will be held in Doha, Qatar during January 1-4, 2019.

AIAIM2019 (Call for Paper) aims to provide a high-level international forum for scientists, engineers, and educators to present the state of the art of research and applications in artificial intelligence, especially the applications to intelligent manufacturing. The conference will feature plenary speeches given by world renowned scholars, regular sessions with broad coverage, and special sessions focusing on popular topics. The proceedings of AIAIM2019 will be submitted for inclusion into the IEEE Xplore Database which is indexed by EI Compendex.

AIAIM2019 is sponsored by Texas A&M University at Qatar, Doha, Qatar and Northeastern University, Shenyang, China, technically sponsored by IEEE Systems, Man, and Cybernetics Society. We strongly believe that this conference will advance Qatar's culture of research and development, promote the collaborations between researchers and scholars from Qatar and researchers and scientists from other countries, especially from China.

下载Call4Papers App，获取更多详细内容！