Filters








3,940 Hits in 5.7 sec

A Deep Learning Approach for Predicting Process Behaviour at Runtime [chapter]

Joerg Evermann, Jana-Rebecca Rehse, Peter Fettke
2017 Lecture Notes in Business Information Processing  
for deep learning methods.  ...  This in turn requires accurate prediction models for process outcomes and for the next process event, based on runtime information available at the prediction and decision point.  ...  The aim of this paper is to explore the potential for applications of deep learning in business process management at runtime and to describe an initial application.  ... 
doi:10.1007/978-3-319-58457-7_24 fatcat:djct3qpiqbebbp2ffuyy6s24vu

Towards the Safety of Human-in-the-Loop Robotics: Challenges and Opportunities for Safety Assurance of Robotic Co-Workers [article]

Kerstin Eder, Chris Harper, Ute Leonards
2014 arXiv   pre-print
In this paper we discuss the state of the art in safety assurance, existing as well as emerging standards in this area, and the need for new approaches to safety assurance in the context of learning machines  ...  The success of the human-robot co-worker team in a flexible manufacturing environment where robots learn from demonstration heavily relies on the correct and safe operation of the robot.  ...  ACKNOWLEDGMENT The authors would like to thank Chris Melhuish, Anthony Pipe and Dejanira Araiza Illan for fruitful discussions and feedback.  ... 
arXiv:1404.2229v3 fatcat:ug5puzhzunduxmzspua62u3vce

Lazy Evaluation of Convolutional Filters [article]

Sam Leroux, Steven Bohez, Cedric De Boom, Elias De Coninck, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt
2016 arXiv   pre-print
In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network.  ...  This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements.  ...  Steven Bohez is funded by a PhD grant of the Agency for Innovation by Science and Technology in Flanders (IWT). Cedric De Boom is funded by a PhD grant of the Flanders Research Foundation (FWO).  ... 
arXiv:1605.08543v1 fatcat:wjrsd4nmwnaafd23z3eusgsmye

Towards the safety of human-in-the-loop robotics: Challenges and opportunities for safety assurance of robotic co-workers'

Kerstin Eder, Chris Harper, Ute Leonards
2014 The 23rd IEEE International Symposium on Robot and Human Interactive Communication  
In this paper we discuss the state of the art in safety assurance, existing as well as emerging standards in this area, and the need for new approaches to safety assurance in the context of learning machines  ...  The success of the human-robot co-worker team in a flexible manufacturing environment where robots learn from demonstration heavily relies on the correct and safe operation of the robot.  ...  ACKNOWLEDGMENT The authors would like to thank Chris Melhuish, Anthony Pipe and Dejanira Araiza Illan for fruitful discussions and feedback.  ... 
doi:10.1109/roman.2014.6926328 dblp:conf/ro-man/EderHL14 fatcat:bd3nylecr5fplojunjoaczgrte

State of runtime adaptation in service-oriented systems: what, where, when, how and right

Leah Mutanu, Gerald Kotonya
2019 IET Software  
Dynamic adaptation has been proposed as a way to address the problem. However, for adaptation to be effective several other factors need to be considered.  ...  Software as a Service reflects a 'service-oriented' approach to software development that is based on the notion of composing applications by discovering and invoking network-available services to accomplish  ...  They state that formal methods can be used as a rigorous means for specifying and reasoning about self-adaptive systems' behaviour, both at design time and at runtime.  ... 
doi:10.1049/iet-sen.2018.5028 fatcat:vkdm64yvybhj5gsptqybj3y6wu

An Enhanced Classification Model for Likelihood of Zero-Day Attack Detection and Estimation

Victor T. Emmah, Chidiebere Ugwu, Laeticia N. Onyejegbu
2021 European Journal of Electrical Engineering and Computer Science  
The technique employs a Monte Carlo Based Pareto Rule (Deep-RL-MCB-PR) approach that exploits a reward learning and training feature with sparse feature generation and adaptive multi-layered recurrent  ...  In this paper a zero-day vulnerability model based on deep-reinforcement learning is presented.  ...  This can be concluded that using a Deep-learning approach for zero-day detection and prioritization is better compared to using a rule-based approach. VI.  ... 
doi:10.24018/ejece.2021.5.4.350 fatcat:s3g3i7burnaf3p5wrbtibesahq

Estimating the Circuit Deobfuscating Runtime based on Graph Deep Learning [article]

Zhiqian Chen, Gaurav Kolhe, Setareh Rafatirad, Sai Manoj P. D., Houman Homayoun, Liang Zhao, Chang-Tien Lu
2020 arXiv   pre-print
To address the above mentioned challenges, this work proposes the first machine-learning framework that predicts the deobfuscation runtime based on graph deep learning techniques.  ...  for deobfuscation.  ...  GCNs, as a state-of-the-art deep learning method for the graph, focus on processing graph signals defined on undirected graphs.  ... 
arXiv:1902.05357v2 fatcat:cmqk5xqqnzhq5gvxpypjfbojqi

Towards Blockchain-Based Federated Machine Learning: Smart Contract for Model Inference

Vaidotas Drungilas, Evaldas Vaičiukynas, Mantas Jurgelaitis, Rita Butkienė, Lina Čeponienė
2021 Applied Sciences  
Federated learning is a branch of machine learning where a shared model is created in a decentralized and privacy-preserving fashion, but existing approaches using blockchain are limited by tailored models  ...  The overhead tends to diminish at large dataset sizes with the runtime depending on the network size linearly, where additional peers increased the runtime by 6.3 and 6.6 s for 2D and EEG datasets, respectively  ...  [28] proposed a cooperative decentralized deep learning architecture.  ... 
doi:10.3390/app11031010 fatcat:4sr2cr3mnndf7m5mbw4ezsdwky

Machine Learning in Compiler Optimisation [article]

Zheng Wang, Michael O'Boyle
2018 arXiv   pre-print
We then provide a comprehensive survey and provide a road map for the wide variety of different research areas.  ...  In the last decade, machine learning based compilation has moved from an an obscure research niche to a mainstream activity.  ...  Both studies demonstrate the usefulness of large code bases and deep learning techniques for learning predictive models for compiler optimizations.  ... 
arXiv:1805.03441v1 fatcat:bhd7mpl6lzaedbuy7iln4hntki

CPS data streams analytics based on machine learning for Cloud and Fog Computing: A survey

Xiang Fei, Nazaraf Shah, Nandor Verba, Kuo-Ming Chao, Victor Sanchez-Anguix, Jacek Lewandowski, Anne James, Zahid Usman
2019 Future generations computer systems  
To the best of our knowledge, this paper is the first to systematically study machine learning techniques for CPS data stream analytics from various perspectives, especially from a perspective that leads  ...  Cloud and Fog computing has emerged as a promising paradigm for the Internet of things (IoT) and cyber-physical systems (CPS).  ...  Other approaches opt for avoiding online bagging at the forest level, and the subsampling is carried out at the tree level [156] .  ... 
doi:10.1016/j.future.2018.06.042 fatcat:kj722esur5g5vinajrdanunjw4

Smart, adaptive mapping of parallelism in the presence of external workload

M. K. Emani, Zheng Wang, M. F. P. O'Boyle
2013 Proceedings of the 2013 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)  
This learned model is then evaluated to make a prediction on the removed sample. This process is repeated for all examples in the training-set.  ...  PEMOGEN [Bhattacharyya and Hoefler 2014] is a framework that learns program performance models at runtime.  ... 
doi:10.1109/cgo.2013.6495010 dblp:conf/cgo/EmaniWO13 fatcat:ebxa4mr5qzcp5ifbiix23eyc4u

Using Machine Learning to Emulate Agent-Based Simulations [article]

Claudio Angione, Eric Silverman, Elisabeth Yaneske
2021 arXiv   pre-print
Here we compare multiple machine-learning methods for ABM emulation in order to determine the approaches best suited to emulating the complex behaviour of ABMs.  ...  We propose that agent-based modelling would benefit from using machine-learning methods for emulation, as this can facilitate more robust sensitivity analyses for the models while also reducing CPU time  ...  Our results suggest that a deep learning approach (using multi-layered neural networks) is the most promising candidate to create a surrogate of the ABM.  ... 
arXiv:2005.02077v2 fatcat:rfwgotphkfgllo2pesvw6z3e6y

PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving [article]

Henry Pulver, Francisco Eiras, Ludovico Carozza, Majd Hawasly, Stefano V. Albrecht, Subramanian Ramamoorthy
2021 arXiv   pre-print
On the other hand, naively deploying trajectories produced by efficient-to-run deep imitation learning approaches might risk compromising safety.  ...  Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving.  ...  an external route planner; and 3) predicted traces for all road users provided by a prediction module.  ... 
arXiv:2011.00509v3 fatcat:aesgsiduf5bdbpo6yvivwjcxpe

Toward a Deep Learning-Driven Intrusion Detection Approach for Internet of Things [article]

Mengmeng Ge, Naeem Firdous Syed, Xiping Fu, Zubair Baig, Antonio Robles-Kelly
2020 arXiv   pre-print
In this paper, we present a novel intrusion detection approach for IoT networks through the application of a deep learning technique.  ...  Results obtained through the evaluation of the proposed approach demonstrate a high classification accuracy for both binary and multi-class classifiers.  ...  In this work, we propose a novel intrusion detection approach against cyber attacks for IoT networks based upon the concept of deep learning.  ... 
arXiv:2007.09342v1 fatcat:m6jttbvoyrbwxiupwargkbihve

Active Reinforcement Learning – A Roadmap Towards Curious Classifier Systems for Self-Adaptation [article]

Simon Reichhuber, Sven Tomforde
2022 arXiv   pre-print
learning, for instance.  ...  The idea of this article is to present a concept for alleviating these drawbacks by setting up a research agenda towards what we call "active reinforcement learning" in intelligent systems.  ...  A keystone in this definition is the ability of an intelligent system to learn autonomously at runtime (D'Angelo et al., 2019) .  ... 
arXiv:2201.03947v1 fatcat:6dgept56bfg2bdiqvvlrlm6ha4
« Previous Showing results 1 — 15 out of 3,940 results