Issues on building software for hardware agents

1995 ◽  
Vol 10 (3) ◽  
pp. 301-304 ◽  
Author(s):  
Henry Hexmoor ◽  
David Kortenkamp
Keyword(s):  
Artificial Intelligence ◽  
Short Range ◽  
Middle Layer ◽  
Hierarchical Architecture ◽  
Small Community ◽  
Reactive Control ◽  
Layered Architecture ◽  
Community Of Researchers ◽  
Prior Experiences ◽  
Modelling System

James Albus states that “an architecture is a description of how a system is constructed from basic components and how those components fit together to form the whole” (Albus, 1995). A software architecture for physical agents reflects the organising principles that its designers have learned from many prior experiences in building such agents. Architectures that have been proposed for physical agents have differed greatly—from subsumption (Brooks, 1986) to Soar (Laird et al., 1987). However, a surprising consensus about architectures is beginning to emerge within the small community of researchers applying artificial intelligence to robotics. The consensus is that a multi- layer, hierarchical architecture is necessary. In particular, the community is moving towards a three-layered architecture. The lowest layer is a reactive control system inspired by subsumption (Brooks, 1986). The top layer is a traditional symbolic planning and modelling system. The middle layer is the key; it serves as a “differential” between the short-range reaction and long-range reasoning.

scholarly journals Five Years of Argument Mining: a Data-driven Analysis

2018 ◽  
Author(s):  
Elena Cabrio ◽  
Serena Villata
Keyword(s):  
Artificial Intelligence ◽  
Computational Models ◽  
Research Area ◽  
Research Topic ◽  
Structured Data ◽  
Data Driven ◽  
Small Community ◽  
Research Areas ◽  
Open Discussion ◽  
Community Of Researchers

Argument mining is the research area aiming at extracting natural language arguments and their relations from text, with the final goal of providing machine-processable structured data for computational models of argument. This research topic has started to attract the attention of a small community of researchers around 2014, and it is nowadays counted as one of the most promising research areas in Artificial Intelligence in terms of growing of the community, funded projects, and involvement of companies. In this paper, we present the argument mining tasks, and we discuss the obtained results in the area from a data-driven perspective. An open discussion highlights the main weaknesses suffered by the existing work in the literature, and proposes open challenges to be faced in the future.

scholarly journals A Fog Computing Architecture with Multi-Layer for Computing-Intensive IoT Applications

2021 ◽  
Vol 11 (24) ◽  
pp. 11585
Author(s):  
Muhammad Muneeb ◽  
Kwang-Man Ko ◽  
Young-Hoon Park
Keyword(s):  
Artificial Intelligence ◽  
Data Analysis ◽  
New Technologies ◽  
Fog Computing ◽  
Layered Architecture ◽  
Computing Platform ◽  
Computing Paradigm ◽  
Iot Devices ◽  
Analysis System ◽  
Data Analysis System

The emergence of new technologies and the era of IoT which will be based on compute-intensive applications. These applications will increase the traffic volume of today’s network infrastructure and will impact more on emerging Fifth Generation (5G) system. Research is going in many details, such as how to provide automation in managing and configuring data analysis tasks over cloud and edges, and to achieve minimum latency and bandwidth consumption with optimizing task allocation. The major challenge for researchers is to push the artificial intelligence to the edge to fully discover the potential of the fog computing paradigm. There are existing intelligence-based fog computing frameworks for IoT based applications, but research on Edge-Artificial Intelligence (Edge-AI) is still in its initial stage. Therefore, we chose to focus on data analytics and offloading in our proposed architecture. To address these problems, we have proposed a prototype of our architecture, which is a multi-layered architecture for data analysis between cloud and fog computing layers to perform latency- sensitive analysis with low latency. The main goal of this research is to use this multi-layer fog computing platform for enhancement of data analysis system based on IoT devices in real-time. Our research based on the policy of the OpenFog Consortium which will offer the good outcomes, but also surveillance and data analysis functionalities. We presented through case studies that our proposed prototype architecture outperformed the cloud-only environment in delay-time, network usage, and energy consumption.

AN EXTENSIBLE ARCHITECTURE-BASED FRAMEWORK FOR COORDINATION LANGUAGES

2004 ◽  
Vol 13 (01) ◽  
pp. 37-61
Author(s):  
TORSTEN FINK ◽  
KARSTEN OTTO
Keyword(s):  
Middle Layer ◽  
Distributed Applications ◽  
Target System ◽  
Layered Architecture ◽  
Component Systems ◽  
Coordination Languages ◽  
Coordination Systems ◽  
Coordination Framework ◽  
Time Overhead ◽  
Different Levels

The dynamic and heterogeneous nature of distributed systems makes the development of distributed applications a difficult task. Various tools, such as middleware systems, component systems, and coordination languages, offer support the application developer at different levels. There are several coordination systems that integrate such tools into a complete environment to build applications from heterogeneous components. To achieve extensibility they usually have a layered architecture: an application is first mapped to a middle layer and then to a target system. But this approach hides the specific features of a target system from the developer, as they are not represented in the middle layer, and often induces additional run-time overhead. In this paper, we introduce the extensible coordination framework ECF that allows developers to build efficient distributed applications which exploit the specific features of the target systems. Support for target systems and application domains are encapsulated by extension modules. Modules can be built on top of other modules to support refined functionality.

scholarly journals Training translators to use corpora hands-on: challenges and reactions by a group of thirteen students at a UK university

Corpora ◽  
2015 ◽  
Vol 10 (3) ◽  
pp. 351-380 ◽  
Author(s):  
Ana Frankenberg-Garcia
Keyword(s):  
Language Processing ◽  
Translation Studies ◽  
Small Community ◽  
Language Resources ◽  
Internet Connection ◽  
Translation Practice ◽  
Hands On ◽  
Self Reports ◽  
Community Of Researchers ◽  
The University

The use of corpora is no longer restricted to a small community of researchers working on language description and natural language processing. Anyone with an Internet connection is now able to access corpora to help them with everyday questions about language, including questions for which dictionaries, grammars and other language resources do not always have clear answers. Translators are among those who have much to gain from using corpora, and this is widely acknowledged in the literature. Yet much of the research at the crossroads of translation and corpora seems to focus on the use of corpora in Translation Studies, and there does not seem to be enough information on the use of corpora in actual translation training and practice. In this paper, I discuss some of the challenges of training translators to use corpora and then describe how a group of thirteen students studying for an MA in Translation at the University of Surrey reacted to a hands-on module on learning to use corpora in everyday translation. The latter is based on the students’ responses to a questionnaire and on a corpus of self-reports containing authentic examples of students using corpora in translation practice.

scholarly journals Self-Supervised Variational Auto-Encoders

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 747
Author(s):  
Ioannis Gatopoulos ◽  
Jakub M. Tomczak
Keyword(s):  
Artificial Intelligence ◽  
Density Estimation ◽  
Latent Variable ◽  
Image Data ◽  
Generative Models ◽  
Hierarchical Architecture ◽  
Data Reconstruction ◽  
Use Case ◽  
Data Generation ◽  
Trade Off

Density estimation, compression, and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE), which utilizes deterministic and discrete transformations of data. This class of models allows both conditional and unconditional sampling while simplifying the objective function. First, we use a single self-supervised transformation as a latent variable, where the transformation is either downscaling or edge detection. Next, we consider a hierarchical architecture, i.e., multiple transformations, and we show its benefits compared to the VAE. The flexibility of selfVAE in data reconstruction finds a particularly interesting use case in data compression tasks, where we can trade-off memory for better data quality and vice-versa. We present the performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA).

scholarly journals Interactive Placemaking - Prototype of an Intelligent Urban Building Infrastructure for Critical Borderlands / Kinmen

2018 ◽  
Vol 12 (7) ◽  
pp. 128
Author(s):  
Li-Yen Hsu
Keyword(s):  
Artificial Intelligence ◽  
Fault Tolerance ◽  
Communication Networks ◽  
Rural Areas ◽  
Electromagnetic Interference ◽  
Short Range ◽  
Spider Web ◽  
Dedicated Short Range Communication ◽  
Sensor Information ◽  
Hub Airport

Dependable capabilities to counter wicked tasks are proactively needed for borderland placemaking. Initiated recently, in Xiamen, a hub airport is being constructed at Xiangan district’s Dadeng islet, which was taken after the inner war from the outlying borderland of Taiwan - Kinmen. To promote current interactive urbanizing, holistic pervasiveness, and/or resource chaining, a sensor-information infrastructure with availability, reliability, and maintainability features through artificial intelligence -i.e., the plural surveillances, similar in sensing through creatures’ eyes, ears, and nostrils- is prototyped. By plural detection along traffic paths, such dedicated short-range communication networks, evidenced with terrorist uncertainty, can help promote trust, inclusive accessibility, mobile services, and interactive measures, with fault tolerance, Hamiltonian (a mathematical order), connectivity, scalability, electromagnetic interference countering, and reliable accuracy. More flexibility can be justified for the emerging pervasive logistic and security management demand by further applying other network types. The cube-connected cycle is prototyped for the probe application along waterways and in rural areas. The prototyped spider-web network can be resiliently integrated with shorelines and interior paths and configured together into a featured urban building context, radial-ring, whose sustainability is culturally resonated in world heritage, neighboring Tulous; help promote peace developing and evoke economic interactions, globally.

States and transitions: The trajectory of an idea, 1970-2010

2011 ◽  
Vol 57 (1-2) ◽  
pp. 17-22 ◽  
Author(s):  
Brian Walker ◽  
Mark Westoby
Keyword(s):  
Ecosystem Dynamics ◽  
Range Management ◽  
Small Community ◽  
Community Of Researchers

State-and-transition language for ecosystem dynamics was articulated in a 1989 paper written by Imanuel Noy-Meir in collaboration with Westoby and Walker. That paper has been surprisingly influential considering that the publication it appeared in,Journal of Range Management, serves a relatively small community of researchers. Here we trace the wider history within which the paper sits, both the context that led up to its being written and its influence subsequently. Our aim is to explain Noy-Meir's distinctive and constructive role, at several points in the history.

Sign in / Sign up

Export Citation Format

Share Document