Filters








110,304 Hits in 3.1 sec

Resource Aware ML [chapter]

Jan Hoffmann, Klaus Aehlig, Martin Hofmann
2012 Lecture Notes in Computer Science  
In this tool paper, we describe Resource Aware ML (RAML), a functional programming language that implements our analysis.  ...  Recently, we developed a novel multivariate amortized resource analysis that automatically computes polynomial resource bounds for first-order functional programs.  ...  We implemented our multivariate amortized resource analysis in Resource Aware ML (RAML), a first-order, functional language with an ML-like syntax.  ... 
doi:10.1007/978-3-642-31424-7_64 fatcat:nuabi44amzhybhsbmldiplwoqq

Arrays and References in Resource Aware ML *

Benjamin Lichtman, Jan Hoffmann
unpublished
This article introduces a technique to accurately perform static prediction of resource usage for ML-like functional programs with references and arrays.  ...  As a result, existing automatic amortized analysis systems for ML-like programs cannot derive bounds for programs whose resource consumption depends on data in such structures.  ...  Many of the features for strict functional programs have been combined in Resource Aware ML [19] .  ... 
fatcat:fv4mvwh7bvh5dk2h6dbbwuoqjq

A Flexible Machine Learning-Aware Architecture for Future WLANs [article]

Francesc Wilhelmi, Sergio Barrachina-Muñoz, Boris Bellalta, Cristina Cano, Anders Jonsson, Vishnu Ram
2020 arXiv   pre-print
Lots of hopes have been placed on Machine Learning (ML) as a key enabler of future wireless networks.  ...  Finally, we showcase the superiority of the architecture through an ML-enabled use case for future networks.  ...  It is then required for ML methods to be aware of those devices, so that unfair situations are avoided.  ... 
arXiv:1910.03510v3 fatcat:ixv7msbwhnho7d7d64builtv7e

Towards Real-time Learning for Edge-Cloud Continuum with Vehicular Computing

Ella Peltonen, Arun Sojan, Tero Paivarinta
2021 2021 IEEE 7th World Forum on Internet of Things (WF-IoT)  
To have any use, the information delivery and decision making based on the data require efficient learning models together with dynamically deployed computing and network resources.  ...  New software-defined computing and networking approaches and architectures are required to orchestrate the numerous connected resources dynamically, controllably, and securely along with the evolving needs  ...  Based on this rationale, we emphasise the following open challenges to be solved before the ML/AI pipelines can be fully integrated into the vehicular edge-cloud continuum: Resource-efficient ML/AI and  ... 
doi:10.1109/wf-iot51360.2021.9595628 fatcat:7jarunn6t5ewbeu22jjxcahrdm

Risk-Aware Resource Allocation for URLLC: Challenges and Strategies with Machine Learning [article]

Amin Azari, Mustafa Ozger, Cicek Cavdar
2018 arXiv   pre-print
Hence, in this paper, we first study the coexistence design challenges, especially the radio resource management (RRM) problem and propose a distributed risk-aware ML solution for RRM.  ...  Machine learning (ML) is an important enabler for such a co-existence scenario due to its ability to exploit spatial/temporal correlation in user behaviors and use of radio resources.  ...  Hence, in this paper, we first study the coexistence design challenges, especially the radio resource management (RRM) problem and propose a distributed risk-aware ML solution for RRM.  ... 
arXiv:1901.04292v1 fatcat:yy6vsbpp5ngvhhzydswl5ttbqa

Data-sharing markets for integrating IoT data processing functionalities

Nasr Kasrin, Aboubakr Benabbas, Golnaz Elmamooz, Daniela Nicklas, Simon Steuer, Michael Sünkel
2021 CCF Transactions on Pervasive Computing and Interaction  
For the first, we focus on the following challenges: sensor data quality, privacy in data streams, machine learning model management, and resource-aware data management.  ...  In addition, data-sharing markets themselves can be combined into networks of markets where information flows from one market to another, which creates a web of information exchange about data resources  ...  tackle the management problem from a resource-aware approach, which we call the CResource challenge.  ... 
doi:10.1007/s42486-020-00054-y fatcat:fyjfrti5fbdutjiapnqt44hwm4

Energy and Thermal-aware Resource Management of Cloud Data Centres: A Taxonomy and Future Directions [article]

Shashikant Ilager, Rajkumar Buyya
2021 arXiv   pre-print
This paper investigates the existing resource management approaches in Cloud Data Centres for energy and thermal efficiency.  ...  It identifies the need for integrated computing and cooling systems management and learning-based solutions in resource management systems.  ...  Many researchers have proposed energy-aware resource provisioning techniques. Authors in [132] investigated energy-aware resource allocation for scientific applications.  ... 
arXiv:2107.02342v1 fatcat:zjmghuyhwbd6nhag4txpvgg5wi

Towards Fairness-Aware Multi-Objective Optimization [article]

Guo Yu, Lianbo Ma, Wei Du, Wenli Du, Yaochu Jin
2022 arXiv   pre-print
However, much less attention has been paid to the fairness-aware multi-objective optimization, which is indeed commonly seen in real life, such as fair resource allocation problems and data driven multi-objective  ...  Finally, challenges and opportunities in fairness-aware multi-objective optimization are addressed.  ...  In recent years, fairness-aware federated learning has become a hot topic in ML [9] for the following reasons.  ... 
arXiv:2207.12138v1 fatcat:oevlblgrlrg3xcxq7wjooxhpgm

Intelligent Radio: When Artificial Intelligence Meets the Radio Network

Tao Chen, Hsiao-Hwa Chen, Zheng Chang, Shiwen Mao
2020 IEEE wireless communications  
Qin et al., introduces recent advances in ML in wireless communications. It briefly introduces deep learning applied for physical layer communications and resource allocation.  ...  It calls for interdisciplinary research to integrate the advances in AI/ML, communications, computing, and cloud technologies.  ...  Three articles handle the modeling issues in wireless systems when AI/ML is considered. In the article "A Deep-Tree-Model-Based Radio Resource Distribution for 5G Networks," M.  ... 
doi:10.1109/mwc.2020.9023916 fatcat:5o2yvxnb3zhy5hd6af7g7kb3ly

Page 125 of Library Resources & Technical Services Vol. 46, Issue 4 [page]

2002 Library Resources & Technical Services  
) are either working on implementing such a mecha- nism or are aware that they need one.  ...  In addition, 34 libraries (20.5%) have put together a collection of resources (28.7% on diversity and multiculturalism, 47 libraries have developed community outreach partnerships with ML groups to shape  ... 

Dynamic Spectrum Allocation Following Machine Learning-Based Traffic Predictions in 5G

Rakibul Islam Rony, Elena Lopez-Aguilera, Eduard Garcia-Villegas
2021 IEEE Access  
In this way, frequency resources are becoming one of the most valuable assets, which require proper utilization and fair distribution.  ...  These static approaches tend to cause congestion in a few cells, whereas at the same time, might waste those precious resources on others.  ...  Therefore, in this era of automation, future cellular networks are expected to adopt ML techniques to perform dynamic resource allocations.  ... 
doi:10.1109/access.2021.3122331 fatcat:zqxqy54h2zd6nojrizux7dn3p4

Supervised-learning-Based QoE Prediction of Video Streaming in Future Networks: A Tutorial with Comparative Study

Arslan Ahmad, Atif Bin Mansoor, Alcardo Alex Barakabitze, Andrew Hines, Luigi Atzori, Ray Walshe
2021 IEEE Communications Magazine  
management where machine learning (ML) can play a crucial role.  ...  ) based service management remains key for successful provisioning of multimedia services in next-generation networks such as 5G/6G, which requires proper tools for quality monitoring, prediction and resource  ...  The output of the trained ML model, the estimated QoE is reported to the QoE prediction module which stores the predicted/measured QoE data and make it available to the QoE-aware Network Resource Management  ... 
doi:10.1109/mcom.001.2100109 fatcat:sseghpitfzerzgqgd6ncgq6ge4

RANDOMISED DOUBLE-BLIND STUDY OF INTRATHECAL BUPIVACAINE-MORPHINE VERSUS SYSTEMIC MORPHINE ANALGESIA FOR MAJOR ABDOMINAL SURGERY IN A RESOURCE POOR SETTING
English

Shreyasi Ray, Jyotirmay Kirtania
2017 Journal of Evolution of Medical and Dental Sciences  
There were no significant differences in intraoperative vasopressor consumption, the postoperative OASS scores, first 24h urine output, incidence of postoperative nausea and vomiting and Michigan Awareness  ...  Randomised double-blind study of intrathecal bupivacaine-morphine versus systemic morphine analgesia for major abdominal surgery in a resource poor setting.  ...  Awareness reports were classified as: (1) No awareness or awareness of something with a high probability of occurring in the immediate preoperative or postoperative period, (2) Possible awareness: patient  ... 
doi:10.14260/jemds/2017/1161 fatcat:sppl2kr2qzasdbl5bibmwjhyde

SLA-Driven ML Inference Framework for Clouds with Hetergeneous Accelerators

Junguk Cho, Diman Zad Tootaghaj, Lianjie Cao, Puneet Sharma
2022 Conference on Machine Learning and Systems  
To address these challenges, we propose SLA-aware ML Inference Framework, which is a novel application and hardwareaware serverless computing framework to manage ML (e.g., DNN) inference applications in  ...  In addition, our framework enables efficient shares of GPU accelerators with multiple functions to increase resource efficiency with minimal overhead.  ...  (i) We propose SMIF (short for SLA-driven ML inference framework), a heterogeneity-aware serverless framework for ML inference services on heterogeneous infrastructure to address those challenges.  ... 
dblp:conf/mlsys/ChoTCS22 fatcat:uxfzaro2lza3ti7bfhe3onhqcq

Distributed dynamic spectrum access with adaptive power allocation: Energy efficiency and cross-layer awareness

Mahdi Ben Ghorbel, Bechir Hamdaoui, Rami Hamdi, Mohsen Guizani, MohammadJavad NoroozOliaee
2014 2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)  
This paper proposes energy and cross-layer aware resource allocation techniques that allow dynamic spectrum access users, by means of learning algorithms, to locate and exploit unused spectrum opportunities  ...  Index Terms-Cross-layer resource allocation, dynamic spectrum access, distributed resource sharing, private objective functions, cognitive radio networks.  ...  This quantity is bounded from above by 2 ml (since m max i ≤ ml and ml j=0 ml j = 2 ml ).  ... 
doi:10.1109/infcomw.2014.6849315 dblp:conf/infocom/GhorbelHHGN14 fatcat:ketjyb3c6jhevpmyfwnwjpxyge
« Previous Showing results 1 — 15 out of 110,304 results