Filters








4,634 Hits in 5.7 sec

Intelligate: Scalable Dynamic Invariant Learning for Power Reduction [chapter]

Roni Wiener, Gila Kamhi, Moshe Y. Vardi
2009 Lecture Notes in Computer Science  
Our approach focuses upon dynamic simulation data as the main source for detection of opportunities for power reduction.  ...  In this work we introduce an enhanced methodology to detect dynamic invariants from a power-benchmark simulation trace database.  ...  Overview of Intelligate Intelligate is a framework that aims at dynamic-power reduction through clock gating.  ... 
doi:10.1007/978-3-540-95948-9_6 fatcat:e53kxaeek5hkxohocplxilhwqe

QUO VADIS, COMPUTATIONAL INTELLIGENCE? [chapter]

WŁODZISŁAW DUCH, JACEK MAŃDZIUK
2004 Advances in Fuzzy Systems — Applications and Theory  
What are the most important problems of computational intelligence? A sketch of the road to intelligent systems is presented.  ...  Acknowledgments We would like to thank our expert colleagues who supported this project by sending descriptions of problems that according to them are the most challenging issues in the field of computational intelligence  ...  Ideally, large, scalable network structures should be suited to immediate, one pass incremental learning schemes.  ... 
doi:10.1142/9789812562531_0001 fatcat:lk3kdecperbt3aynsbd7jnqsoe

Intelligent Network Client Profiler

Diogo Teixeira, Artur Arsénio
2013 Journal of Advances in Computer Networks  
However, the main obstacle to this identification is the lack of scalability for monitoring network devices. In particular, they can analyze all the network packets for this purpose.  ...  Thus it becomes possible to get ISPs to optimize their network in a scalable and intelligent manner, imposing security measures in order to enforce network usage according to client profiles.  ...  It is proposed an intelligent and scalable algorithm for real-time traffic analysis.  ... 
doi:10.7763/jacn.2013.v1.26 fatcat:cilfbhxuwrfxxjrkewxhitkc24

Deep Reinforcement Learning as Foundation for Artificial General Intelligence [chapter]

Itamar Arel
2012 Atlantis Thinking Machines  
Analog computation also frequently comes with a significant reduction in power consumption, which will become critical as powerful learning systems are migrated to battery-operated platforms.  ...  The merger between deep architectures as scalable state inference engines and reinforcement learning as a powerful control framework offers the potential for an AGI breakthrough.  ... 
doi:10.2991/978-94-91216-62-6_6 fatcat:sqo63ghxcrfhhd32eiiez67dbq

Intelligent, smart and scalable cyber-physical systems

V. Vijayakumar, V. Subramaniyaswamy, Jemal Abawajy, Longzhi Yang, V. Vijayakumar, V. Subramaniyaswamy, Jemal Abawajy, Longzhi Yang
2019 Journal of Intelligent & Fuzzy Systems  
These challenges range from the design of intelligent physical infrastructures for sensing and communication, data stream processing, data analytics and machine learning techniques to build the intelligence  ...  The rapidly growing interconnections between the virtual and physical worlds and the development of new intelligent techniques have created new opportunities for the research for next-generation CPS, that  ...  Reza Langari for his supportive guidance during the entire process.  ... 
doi:10.3233/jifs-179108 fatcat:4hghoxr4prccxjpfg5juwzoie4

Intelligent energy management

Seshadri Srinivasa Raghavan, Alireza Khaligh
2012 Proceedings of the Workshop on Performance Metrics for Intelligent Systems - PerMIS '12  
Computational Intelligence (CI) for Smart Grid To achieve these intelligent technologies for Smart Grid which will operate in an extremely complex and dynamic system, it is necessary to use Computational  ...  The potential for application of swarm intelligence to Optimal Reactive Power Dispatch (ORPD) has been shown in this thesis.  ... 
doi:10.1145/2393091.2393118 dblp:conf/permis/RaghavanK12 fatcat:6aldvjh2d5dhbksq47fp765l6q

A Survey on Trusted Distributed Artificial Intelligence

Muhammed Akif Agca, Sebastien Faye, Djamel Khadraoui
2022 IEEE Access  
Therefore, resiliency and robustness can be assured in a dynamic context with an end-to-end Trusted Execution Environment (TEE) for growing intelligent mechanisms and systems.  ...  These challenges and critical feature sets have been identified and introduced into this survey with their scientific background for AI systems and growing intelligent mechanisms.  ...  We can also assume that for some tasks, a given node might rely on the processing power offered (vs allowed) by a remote node due to the lack of processing power or learning capability of the original  ... 
doi:10.1109/access.2022.3176385 fatcat:3snokz5z7rbhff2tde4gnrqf4a

Open Ended Intelligence: The individuation of Intelligent Agents [article]

David Weinbaum, Viktoras Veitas
2015 arXiv   pre-print
We further show how open-ended intelligence can be framed in terms of a distributed, self-organizing network of interacting elements and how such process is scalable.  ...  The framework highlights an important relation between coordination and intelligence and a new understanding of values. We conclude with a number of questions for future research.  ...  In our case it means that for intelligence to manifest, it is necessary for the agent to interact/observe with its environment because only via interactions/observations can it learn what is necessary  ... 
arXiv:1505.06366v2 fatcat:xcq7zytu2vafpo2rvxmhfijcle

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications [article]

Khaled B. Letaief, Yuanming Shi, Jianmin Lu, Jianhua Lu
2021 arXiv   pre-print
In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models.  ...  By embedding model training and inference capabilities into the network edge, edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence  ...  Edge AI: Challenges and Solutions Creating a trustworthy and scalable edge AI system will be of utmost importance for imbuing connected intelligence in 6G.  ... 
arXiv:2111.12444v1 fatcat:crrbtfylvjeihogumggdnxcbpq

Intelligate: An Algorithm for Learning Boolean Functions for Dynamic Power Reduction

Roni Wiener, Gila Kamhi, Moshe Y. Vardi
2009 Journal of Low Power Electronics  
Our approach focus upon dynamic simulation data as the main source for detection of opportunities for power reduction.  ...  for logic correctness and dynamic power reduction upon a set of heldout simulation traces.  ...  power estimation This appendix describes a gross estimation method to estimate the dynamic power consumption of the added gating logic.  ... 
doi:10.1166/jolpe.2009.1009 fatcat:av5a5eei2zamvkrdo5afazx4cu

Taurus: An Intelligent Data Plane [article]

Tushar Swamy, Alexander Rucker, Muhammad Shahbaz, Kunle Olukotun
2020 arXiv   pre-print
In this paper, we present Taurus, an intelligent data plane capable of machine-learning inference at line rate.  ...  Emerging applications -- cloud computing, the internet of things, and augmented/virtual reality -- need responsive, available, secure, ubiquitous, and scalable datacenter networks.  ...  Figure 11 shows that the per-FU area and dynamic power decrease with lane count, because adding lanes or stages decreases the amount of control logic and overhead per FU.  ... 
arXiv:2002.08987v1 fatcat:6hxsnoqxxnglvewm56zl7uzine

Multiversal SpaceTime (MSpaceTime) Not Neural Network as Source of Intelligence in Generalized Quantum Mechanics, Extended General Relativity, Darwin Dynamics for Artificial Super Intelligence Synthesis [article]

Yang Zhang
2019 bioRxiv   pre-print
Relativity, for Artificial Super Intelligence (ASI) implementation.  ...  Intelligence of ASI.  ...  All have to 125 rely on correlation-based anti-reductionism-powered learning approach if causality-based 126 reductionism-powered computing approach does not work well alone. 127 Any living system who  ... 
doi:10.1101/858423 fatcat:o5ove6dmgzc5ng4mc7bonui2sq

Intelligent Video Systems and Analytics: A Survey

Honghai Liu, Shengyong Chen, Naoyuki Kubota
2013 IEEE Transactions on Industrial Informatics  
Recent technology and market trends have demanded the significant need for feasible solutions to video/camera systems and analytics.  ...  Research directions are outlined with a focus on what is essential to achieve the goals of intelligent video systems and analytics.  ...  Learning and Classification Learning and classification are powerful for object detection and event recognition [62] .  ... 
doi:10.1109/tii.2013.2255616 fatcat:53jmubicdrgp7fg3w7zdipd3le

Artificial Intelligence [article]

John Paul Mueller Luca Massaron
2018 Zenodo  
Artificial Intelligence (AI) has had several false starts and stops over the years, partly because people don't really understand what AI is all about, or even what it should accomplish.  ...  Conditional probabilities are a very powerful tool for machine learning and AI.  ...  for military power.  ... 
doi:10.5281/zenodo.5599660 fatcat:rn6nyx5xinehzpwfy3knurtzgy

Artificial Intelligence-Defined 5G Radio Access Networks [article]

Miao Yao, Munawwar Sohul, Vuk Marojevic, Jeffrey H. Reed
2018 arXiv   pre-print
This article discusses the intelligent agent in 5G base station which combines sensing, learning, understanding and optimizing to facilitate these enablers.  ...  We present example AI-enabled 5G use cases that accommodate important 5G-specific capabilities and discuss the value of AI for enabling beyond 5G network evolution.  ...  Walton for his inspirational advice on this article.  ... 
arXiv:1811.08792v2 fatcat:wyhinubtjbbhta4gj4mcwuhgme
« Previous Showing results 1 — 15 out of 4,634 results