Filters








26,055 Hits in 6.3 sec

A Comprehensive Study on Challenges in Deploying Deep Learning Based Software [article]

Zhenpeng Chen and Yanbin Cao and Yuanqiang Liu and Haoyu Wang and Tao Xie and Xuanzhe Liu
2020 arXiv   pre-print
To fill this knowledge gap, this paper presents a comprehensive study on understanding challenges in deploying DL software.  ...  Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications.  ...  To bridge the knowledge gap, this paper presents the first comprehensive empirical study on identifying challenges in deploying DL software.  ... 
arXiv:2005.00760v4 fatcat:auxizifdrbd6ppahv6ji4cvxs4

Secure Deep Learning Engineering: A Software Quality Assurance Perspective [article]

Lei Ma, Felix Juefei-Xu, Minhui Xue, Qiang Hu, Sen Chen, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
2018 arXiv   pre-print
We, from a software quality assurance perspective, pinpoint challenges and future opportunities towards universal secure deep learning engineering.  ...  In this paper, we perform a large-scale study and construct a paper repository of 223 relevant works to the quality assurance, security, and interpretation of deep learning.  ...  We define Secure Deep Learning Engineering (SDLE) as an engineering discipline of deep learning software production, through a systematic application of knowledge, methodology, practice on deep learning  ... 
arXiv:1810.04538v1 fatcat:fbxdxvw55zc7vbkpjm6bpknlby

Software Engineering Practice in the Development of Deep Learning Applications [article]

Xufan Zhang, Yilin Yang, Yang Feng, Zhenyu Chen
2019 arXiv   pre-print
They are constructed based on a data-driven programming paradigm that is different from conventional software applications.  ...  Deep-Learning(DL) applications have been widely employed to assist in various tasks.  ...  This study casts doubts on the necessity of applying deep learning techniques in practice. Amershi et al. [1] report their experience on developing AI-based systems in Microsoft.  ... 
arXiv:1910.03156v1 fatcat:tqfbmzx4n5cufgdjngztflsns4

Multimedia Data Analysis With Edge Computing

Shu-Ching Chen
2021 IEEE Multimedia  
Pouyanfar et al., “A survey on deep learning: Algorithms, analysis at the software level, the software–hardware techniques, and applications  ...  A. Jan, and D. Puthal, “PAAL: A “Membership inference attacks against machine framework based on authentication, aggregation, and learning models,” in Proc.  ... 
doi:10.1109/mmul.2021.3124292 fatcat:kc6nmnnkvbhg3pbyzdqih4ns7y

Challenges in Deploying Machine Learning: a Survey of Case Studies [article]

Andrei Paleyes, Raoul-Gabriel Urma, Neil D. Lawrence
2021 arXiv   pre-print
This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries and applications and extracts practical considerations corresponding to stages of the  ...  However, the deployment of machine learning models in production systems can present a number of issues and concerns.  ...  In this study, we undertake a survey of these reports to capture the current challenges in deploying machine learning in production 1 .  ... 
arXiv:2011.09926v2 fatcat:77pc5hrttnhbfoggpu2xx5g7sy

Machine Learning Software Architecture and Model Workflow. A Case of Django REST Framework

Kennedy Ochilo Hadullo, Daniel Makini Getuno
2021 American Journal of Applied Sciences  
In the end, the study gives a conclusion on how the remedies provided helps to meet the objectives of study.  ...  The purpose of this study was to find out the challenges facing Machine Learning (ML) software development and create a design architecture and a workflow for successful deployment.  ...  Acknowledgement This research was made possible by the support provided by The Technical university of Mombasa and Egerton university through journal subscriptions, need-based acquisition and a favorable  ... 
doi:10.3844/ajassp.2021.152.164 fatcat:ztyr3ealgzhizcinr7wpaepree

Visualized Malware Multi-Classification Framework Using Fine-Tuned CNN-Based Transfer Learning Models

Walid El-Shafai, Iman Almomani, Aala AlKhayer
2021 Applied Sciences  
deep learning (DL)-based malware multi-classification approaches tested on the same malware dataset.  ...  There is a massive growth in malicious software (Malware) development, which causes substantial security threats to individuals and organizations.  ...  models are introduced based on deep learning (DL) approaches.  ... 
doi:10.3390/app11146446 fatcat:ayvvyjwatvboxgholhzxlucg7u

A Survey on Artificial Intelligence Trends in Spacecraft Guidance Dynamics and Control [article]

Dario Izzo and Marcus Märtens and Binfeng Pan
2018 arXiv   pre-print
Our focus is on evolutionary optimisation, tree searches and machine learning, including deep learning and reinforcement learning as the key technologies and drivers for current and future research in  ...  The rapid developments of Artificial Intelligence in the last decade are influencing Aerospace Engineering to a great extent and research in this context is proliferating.  ...  As such, G&CNETs are one of the most promising Deep Learning based technologies that can potentially simplify the on board control and guidance software replacing it with one, relatively simple, trained  ... 
arXiv:1812.02948v1 fatcat:rxrt5mudkzfbzakqesxbivx7ue

Towards Accurate Run-Time Hardware-Assisted Stealthy Malware Detection: A Lightweight, Yet Effective Time Series CNN-Based Approach

Hossein Sayadi, Yifeng Gao, Hosein Mohammadi Makrani, Jessica Lin, Paulo Cesar Costa, Setareh Rafatirad, Houman Homayoun
2021 Cryptography  
In this paper, we first present a comprehensive review of recent advances in hardware-assisted malware detection studies that have used standard ML techniques to detect the malware signatures.  ...  at run-time remains a critical challenge.  ...  Data Availability Statement: The data presented in this study are available in article. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cryptography5040028 fatcat:tdgn54ormvf4tidbwzajazjwky

Transitioning Towards Continuous Delivery in the B2B Domain: A Case Study [chapter]

Olli Rissanen, Jürgen Münch
2015 Lecture Notes in Business Information Processing  
This article presents a case study that is conducted in a medium-sized software company operating in the B2B domain.  ...  The results suggest that technical challenges are only one part of the challenges a company encounters in this transition.  ...  This paper is based on thesis work [13] completed at the University of Helsinki.  ... 
doi:10.1007/978-3-319-18612-2_13 fatcat:25kwupbzbnhthmkujwusbi6md4

SEAA 2020 Opinion

2020 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)  
and leading a research group on Software Engineering Intelligence.  ...  Marouane Kessentini has several collaborations with industry on the use of computational search, machine learning and evolutionary algorithms to address software engineering and services computing problems  ...  Software Engineering Intelligence (SEI) is a new paradigm to address the growing need to combine different types of AI algorithms ranging from metaheuristics search to machine learning, NLP, and deep learning  ... 
doi:10.1109/seaa51224.2020.00009 fatcat:ekfvk57zhbfllntx5i7bmqn3ie

Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency [article]

Cheng-Ming Chiang, Yu Tseng, Yu-Syuan Xu, Hsien-Kai Kuo, Yi-Min Tsai, Guan-Yu Chen, Koan-Sin Tan, Wei-Ting Wang, Yu-Chieh Lin, Shou-Yao Roy Tseng, Wei-Shiang Lin, Chia-Lin Yu (+4 others)
2020 arXiv   pre-print
Moreover, when deploying to different mobile devices, there is a large latency variation due to the difference and limitation of deep learning accelerators on mobile devices.  ...  This paper provides practical deployment-guidelines, and is adopted by the championship-winning team in NTIRE 2020 Image Deblurring Challenge on Smartphone Track.  ...  Introduction Deep learning based networks have achieved great successes in image enhancement and restoration tasks [38, 57, 19, 37, 34] .  ... 
arXiv:2004.12599v1 fatcat:ypbceea67fbtvoe467uergsxwm

Softwarization of UAV Networks: A Survey of Applications and Future Trends

Omar Sami Oubbati, Mohammed Atiquzzaman, Tariq Ahamed Ahanger, Atef Ibrahim
2020 IEEE Access  
Motivated by this fact, in this survey, we guide the reader through a comprehensive discussion of the main characteristics of SDN and NFV technologies.  ...  We then discuss SDN/NFV-enabled UAV-assisted systems, along with several case studies and issues, such as the involvement of UAVs in cellular communications, monitoring, and routing, to name a few.  ...  Another comprehensive study on UAV channel modeling based on low altitude platforms is provided by [35] .  ... 
doi:10.1109/access.2020.2994494 fatcat:irogs7xbvrdpzglyx5jrgjftgm

An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms [article]

Qianyu Guo, Xiaofei Xie, Lei Ma, Qiang Hu, Ruitao Feng, Li Li, Yang Liu, Jianjun Zhao, Xiaohong Li
2018 arXiv   pre-print
Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.  ...  Deep learning (DL) has recently achieved tremendous success in a variety of cutting-edge applications, e.g., image recognition, speech and natural language processing, and autonomous driving.  ...  Related Work In this section, we review the previous work in following three aspects: study on traditional software platforms, study on deep learning frameworks, and study on DL platforms.  ... 
arXiv:1811.05187v1 fatcat:ue33zv7vlbendge446zw4vyesa

Sofware engneering challenges for machine learning applications: A literature review

Fumihiro Kumeno
2020 International Journal of Intelligent Decision Technologies  
Machine learning techniques, especially deep learning, have achieved remarkable breakthroughs over the past decade. At present, machine learning applications are deployed in many fields.  ...  This review paper attempts to clarify the software engineering challenges for machine learning applications that either exist or potentially exist by conducting a systematic literature collection and by  ...  Software engineering economics provides a way to study the attributes of software and software processes in a systematic way that relates them to economic measures."  ... 
doi:10.3233/idt-190160 fatcat:43hceptq3jdmteinoiikvs66ia
« Previous Showing results 1 — 15 out of 26,055 results