8,973 Hits in 4.2 sec

How do People Train a Machine?

Téo Sanchez, Baptiste Caramiaux, Jules Françoise, Frédéric Bevilacqua, Wendy E. Mackay
2021 Proceedings of the ACM on Human-Computer Interaction  
Machine learning systems became pervasive in modern interactive technology but provide users with little, if any, agency with respect to how their models are trained from data.  ...  We developed a web-based sketch recognition algorithm based on Deep Neural Network (DNN), called Marcelle-Sketch, that end-users can train incrementally.  ...  Thanks to Gianni Franchi for his useful thoughts on uncertainty in Deep Neural Networks.  ... 
doi:10.1145/3449236 fatcat:gpt5v3b32jb4vb4fhoptvmnbmu

Style-Aware Sketch-to-Code Conversion for the Web

Tommaso Calò, Luigi De Russis
2022 Companion of the 2022 ACM SIGCHI Symposium on Engineering Interactive Computing Systems  
Recently, a set of Machine Learning techniques has been applied to automatically generate code from sketches to ease this part of the design process.  ...  CCS CONCEPTS • Human-centered computing → Graphical user interfaces; Interface design prototyping; • Computing methodologies → Machine learning; Computer vision.  ...  Pix2code [1] was one of the first works attempting to address the problem of GUI code generation from visual inputs by leveraging machine learning to learn latent variables instead of engineering complex  ... 
doi:10.1145/3531706.3536462 fatcat:lh35xnvulrck3cory6przmh5nm

Challenges in 5G: how to empower SON with big data for enabling 5G

Ali Imran, Ahmed Zoha
2014 IEEE Network  
We then propose a comprehensive framework for empowering SONs with big data to address the requirements of 5G.  ...  We then explicate the specific machine learning and data analytics tools that can be exploited to transform big data into the right data that provides a readily useable knowledge base to create end-to-end  ...  With BSON, these recent developments in machine learning can play a vital role in embedding proactive capabilities in SON for 5G.  ... 
doi:10.1109/mnet.2014.6963801 fatcat:yfsizqlazvanjo4uxhkhvwemia

A Survey on SDN & SDCN Traffic Measurement: Existing Approaches and Research Challenge [article]

MD Samiul Islam, Mojammel Hossain, Mohammed AlMukhtar
2022 arXiv   pre-print
More in details, we list out kinds of practical machine learning (ML) approaches to analyze how we can make improvement in the traffic measurement performances.  ...  Furthermore, we find out the challenges related to SDN/SDCN traffic measurement and future scope of research, which will guide to design and develop more advanced traffic measurement solutions for a scalable  ...  There are several methods using machine learning to deal with this problems. Piamrat et al.  ... 
arXiv:2206.14236v1 fatcat:ziyjpl4o6nctbm5znuhnqsvpm4

SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching [article]

Baolin Peng, Chunyuan Li, Zhu Zhang, Jinchao Li, Chenguang Zhu, Jianfeng Gao
2021 arXiv   pre-print
(ii) Neural learning: The fine-tuned neural dialog model is continually refined with a handful of real task-specific dialogs via machine teaching, where training samples are generated by human teachers  ...  We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on  ...  Q2: How effective is machine teaching for neural learning? Experimental Setup Dataset.  ... 
arXiv:2110.11514v1 fatcat:bc4nucmqpffidjt3sev5hyf64e

Federated Learning in the Lens of Crowdsourcing

Yongxin Tong, Yansheng Wang, Dingyuan Shi
2020 IEEE Data Engineering Bulletin  
We expect to inspire the design of federated learning systems with existing crowdsourcing techniques.  ...  But with more privacy concerns and stricter laws, the data isolation problem is becoming worse, just when federated learning (FL) has emerged as a promising solution.  ...  A special quantization-based technique for gradient compression in FL is proposed in [37] , combined with a periodic averaging learning algorithm. Compression with Sketch.  ... 
dblp:journals/debu/TongWS20 fatcat:6f474mtflfhuffshqltimek5zm

Gesture Recognition Based on Manifold Learning [chapter]

Heeyoul Choi, Brandon Paulson, Tracy Hammond
2008 Lecture Notes in Computer Science  
Effective features for classification can also be automatically learned and chosen by the computer.  ...  In this paper, we develop a new algorithm for multi-stroke gesture recognition, which integrates timing data into a manifold learning algorithm based on a kernel Isomap.  ...  Instructors to Build Sketch Systems in the Classroom.  ... 
doi:10.1007/978-3-540-89689-0_29 fatcat:hxcphhjg5ffgtjkpj5w66iw3je

Intrusion Detection using Machine Learning

2019 International journal of recent technology and engineering  
System savage technicians work to keep administrations accessible every time by dealing with gatecrasher assaults.  ...  This examination work represents how the Knowledge Disclosure and Data Mining (or Knowledge Discovery in Databases) The CART and RBFN have been picked for this investigation.  ...  Almseidin,[6] proposed a detection system called"Machine Learning Methods for Network Intrusion Detection".  ... 
doi:10.35940/ijrte.b1154.0782s619 fatcat:h3wfryaeubbqto6lmgglhy6gzi

Recurrent Neural Networks for real-time distributed collaborative prognostics

Adria Salvador Palau, Kshitij Bakliwal, Maharshi Harshadbhai Dhada, Tim Pearce, Ajith Kumar Parlikad
2018 2018 IEEE International Conference on Prognostics and Health Management (ICPHM)  
We present the first steps towards real-time distributed collaborative prognostics enabled by an implementation of the Weibull Time To Event -Recurrent Neural Network (WTTE-RNN) algorithm.  ...  In our system, assets determine their time to failure (TTF) in real-time according to an asset-specific model that is obtained in collaboration with other similar assets in the asset fleet.  ...  Empowering industrial assets with agents incorporating realtime deep-learning computing capabilities is then likely to be met with reasonable scepticism.  ... 
doi:10.1109/icphm.2018.8448622 dblp:conf/icphm/PalauBDPP18 fatcat:cxhvibcxfbbjbaqcqdzg4exz2u

Industry 4.0 - A New Futuristic Technological Revolution A Catalyst of Innovation & Entrepreneurship in Creation of Enterprises

Industrialization is the crucial arm of an economy which is a dream for every single country on the globe.  ...  This paper manages the investigation of various parts of Industry 4.0 with it's entomb connection with advancement and business cultivating towards big business manifestations and upgrade of worldwide  ...  In short the prime target is to empower machines converse with different machines and items alongside data which is handled and appropriated progressively bringing about significant changes to the whole  ... 
doi:10.35940/ijitee.a5074.119119 fatcat:mt4yzuhywzdlhmwy6oirdmvfya

A survey of sketches in traffic measurement: Design, Optimization, Application and Implementation [article]

Shangsen Li, Lailong Luo, Deke Guo, Qianzhen Zhang, Pengtao Fu
2021 arXiv   pre-print
Finally,we highlight the open issues for future sketch-based network measurement research.  ...  We first introduce the preparation of flows for measurement, then detail the most recent investigations of design, aggregation, decoding, application and implementation of sketches for network measurement  ...  Recently, several studies have combined machine learning (ML) techniques with a measurement framework to relieve or eliminate the binding of traffic flow characteristics and the sketch design.  ... 
arXiv:2012.07214v2 fatcat:lme2ghsshje3tag2m5q3xgvcna

2021 Index IEEE Signal Processing Magazine Vol. 38

2021 IEEE Signal Processing Magazine  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  MSP March 2021 14 Sketching Data Sets for Large-Scale Learning: Keeping Only What You Need.  ...  MSP March 2021 14 Privacy Sketching Data Sets for Large-Scale Learning: Keeping Only What You Need.  ... 
doi:10.1109/msp.2021.3124108 fatcat:ro6fkwa5nndw5i7c3lbq2zljpy

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
Then, we present progress in AI research for IoT from four perspectives: perceiving, learning, reasoning, and behaving.  ...  This paper presents a comprehensive survey on AIoT to show how AI can empower the IoT to make it faster, smarter, greener, and safer.  ...  Thereby, empowering things with learning ability is important for AIoT so that it can update and evolve in response to the variations.  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4

On Training Sketch Recognizers for New Domains [article]

Kemal Tugrul Yesilbek, T. Metin Sezgin
2021 arXiv   pre-print
Furthermore, we demonstrate that in realistic scenarios where data is scarce and expensive, standard measures taken for adapting deep learners to small datasets fall short of comparing favorably with alternatives  ...  We pose learning from small datasets as a key problem for the deep sketch recognition field, one which has been ignored in the bulk of the existing literature.  ...  [37] used deep graphical neural network to achieve stroke-level sketch segmentation. A recent survey of deep learning methods for sketch data by Xu et. al.  ... 
arXiv:2104.08850v1 fatcat:yykeqpp6d5bdhhku4s32bf647q

Design and Implementation of Cloud Analytics-Assisted Smart Power Meters Considering Advanced Artificial Intelligence as Edge Analytics in Demand-Side Management for Smart Homes

Yung-Yao Chen, Yu-Hsiu Lin, Chia-Ching Kung, Ming-Han Chung, I-Hsuan Yen
2019 Sensors  
Therefore, this work designs and implements a smart edge analytics-empowered power meter prototype considering advanced AI in DSM for smart homes.  ...  The experimentation reported in this work shows the architecture described with the prototype in this work is feasible and workable.  ...  Acknowledgments: The authors would also like to thank the reviewers and academic editor for their valuable comments on this work. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19092047 fatcat:67gghin62nh2dmuk6bgbqlucri
« Previous Showing results 1 — 15 out of 8,973 results