A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems
[article]
2018
arXiv
pre-print
Preserved Fulltext
finds the optimal combinations of libraries and primitives to speed up the inference of CNNs on heterogeneous embedded devices. ...
In this work, we present QS-DNN, a fully automatic search based on Reinforcement Learning which, combined with an inference engine optimizer, efficiently explores through the design space and empirically ...
This work is supported by the Swiss State Secretariat for Education Research and Innovation (SERI) under contract number 16.0159. ...
arXiv:1811.07315v1
fatcat:iyyg7uupi5huzeseb22nb7ojcy
Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Meanwhile, deep learning, with many success stories in various disciplines, represents a promising alternative due to its remarkable power to leverage data for problem solving. ...
We first discuss deep learning assisted optimization for resource allocation. ...
Then graph embedding is used to learn the vector representation of each node based on topology information. The output feature vector is then input to a DNN for link scheduling. ...
arXiv:1907.03289v2
fatcat:stvlo3uhqnde3icvovjsrggdwu
Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2006.05181v1 fatcat:xalgaxyb2fgano34ynig4hvagy
The framework relies on a Reinforcement Learning search that, combined with a deep learning inference framework, automatically explores the design space and learns an optimised solution that speeds up ...
The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). ...
Fig. 3 : 3 Architecture of QS-DNN. Complete flow: Inference on an embedded on the left, RL-based learning on the right. ...
arXiv:2006.05181v2
fatcat:bfqm7genmngpxf3lzbpvh6fq3y
Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In WPK, we investigated two new automated search approaches based on genetic algorithm and reinforcement learning, respectively, to hunt the best operator code configurations targeting specific hardware ...
than TensorRT for end-to-end model inference. ...
Conclusion WPK is part of Woodpecker that is an efficient compiler framework for heterogeneous computing based on software-hardware co-design, and targets to accelerate deep learning applications by taking ...
arXiv:2008.04567v1
fatcat:toy3ovoskraavcq3ju36eg4pne
Bonseyes AI Pipeline – bringing AI to you. End-to-end integration of data, algorithms and deployment tools
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Next generation of embedded Information and Communication Technology (ICT) systems are collaborative systems able to perform autonomous tasks. ...
The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one of the keys for the next ...
On the LPDNN side, we employ LNE coupled with an RL-based search (QS-DNN) to find an optimized solution for the deployment on the target platform. ...
arXiv:1901.05049v3
fatcat:dgs4zxtccne5nd4zvt4dqys44y
CLAN: Continuous Learning using Asynchronous Neuroevolution on Commodity Edge Devices
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
With every passing day, deep learning based methods are applied to solve new problems with exceptional results. The portal to the real world is the edge. ...
We build a prototype distributed system of Raspberry Pis communicating via WiFi running NeuroEvolutionary (NE) learning and inference. ...
A fitness value is then assigned based on how well they performed the given task and used to select a few of the fittest members. ...
arXiv:2008.11881v1
fatcat:al7pmoqwy5bafpdyspckbskb44
Transferable Graph Optimizers for ML Compilers
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2010.12438v1 fatcat:ebt3m6m4v5avnasxy6ymol5g2m
To address these limitations, we propose an end-to-end, transferable deep reinforcement learning method for computational graph optimization (GO), based on a scalable sequential attention mechanism over ...
Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. ...
In addition to the model parallelism primitives, GO provides a learning-based optimization that can generalize across different graphs and transfer to new tasks. ...
arXiv:2010.12438v2
fatcat:ju26bxgmajbgfa4wtwvgrc6k2a
Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey
2020
ACM Computing Surveys
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Function-based selection aims to choose an appropriate concept based on their functional difference. ...
Some of these achievements are based on the combination of DL and RL, i.e., Deep Reinforcement Learning. ...
More details of these RL algorithms can be found in the RL methods in Appendix B, and here we focus on selecting appropriate RL algorithms based on different selection criteria.Fig. 8. ...
doi:10.1145/3398020
fatcat:zzgfcjxjxbhnhf53dmlo63rs3i
A Survey on Deep Reinforcement Learning for Data Processing and Analytics
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Next, we discuss DRL deployment on database systems, facilitating data processing and analytics in various aspects, including data organization, scheduling, tuning, and indexing. ...
Motivated by this trend, we provide a comprehensive review of recent works focusing on utilizing DRL to improve data processing and analytics. ...
The DRL agent could learn to understand and solve various tasks with the right incentives. First, we introduce basic foundations and practical techniques in DRL. ...
arXiv:2108.04526v3
fatcat:kcusgp7jzfbf7ov5os7gwf2e6i
Multi-tenant mobile offloading systems for real-time computer vision applications
2019
Proceedings of the 20th International Conference on Distributed Computing and Networking - ICDCN '19
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
To overcome the drawbacks, we further propose an advanced approach based on deep reinforcement learning (RL) [102] . ...
A simple heuristic algorithm and a more advanced algorithm based on deep reinforcement learning (RL) are presented. ...
invoke DNN inference by calling dnn model.detect. ...
doi:10.1145/3288599.3288634
dblp:conf/icdcn/FangLS019
fatcat:qpib2wkm7jdnfg7k64eh3hwje4
Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Based on those approaches, we extrapolate potential directions for parallelism in deep learning. ...
We then review and model the different types of concurrency in DNNs: from the single operator, through parallelism in network inference and training, to distributed deep learning. ...
AmoebaNets outperform all existing methods, including manually engineered DNNs and RL-based searches, with 3.8% error for ImageNet and 2.13% error for CIFAR-10 (compared to 5.29% and 3.62% on the best ...
arXiv:1802.09941v2
fatcat:ne2wiplln5eavjvjwf5to7nwsu
Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper provides a comprehensive and systematic survey on the development lifecycle of ML-based IoT application. ...
Hence, orchestrating ML pipelines that encompasses model training and implication involved in holistic development lifecycle of an IoT application often leads to complex system integration. ...
More details of these RL algorithms can be found in the RL methods in Appendix B, and here we focus on selecting appropriate RL algorithms based on different selection criteria.Fig. 8. ...
arXiv:1910.05433v5
fatcat:ffvjipmylve6feuzdbav2syxfu
A Survey on Reinforcement Learning for Recommender Systems
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems. ...
In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years. ...
For example, in DNNs-based recommender systems, users with fake profiles may be generated to promote selected items. ...
arXiv:2109.10665v2
fatcat:wx5ghn66hzg7faxee54jf7gspq
Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Based on this review, we identify specific open challenges and provide general future research directions. ...
While classical optimization approaches fail in such conditions, machine learning (ML) is able to handle complexity. ...
learned on synthetic Retraining of features improves TL accuracy [223]* RL QL 2020 S Select subchannel new devices Apply RL for subchannel selection considering PHY data to real data Near-optimal system ...
arXiv:2109.04786v3
fatcat:ny55qfhsnfduzcxyve5mylpr2m
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications ...
promoting further discussions on the fusion of edge intelligence and intelligent edge, i.e., Edge DL. ...
Based on such tuple, OpenEI can select a matched model for a specific edge platform based on different Edge DL capabilities in an online manner. ...
arXiv:1907.08349v2
fatcat:4hfqgdto4fhvlguwfjxuz3ik5q
« Previous
Showing results 1 — 15 out of 77 results