Filters








1,555 Hits in 6.5 sec

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [article]

Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer
2020 arXiv   pre-print
In this paper, we review the latest single-source deep unsupervised domain adaptation methods focused on visual tasks and discuss new perspectives for future research.  ...  Domain adaptation is a machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain.  ...  These edge devices are usually deployed in different environments, with substantial need for domain adaptation. Different networks need to be personalized via learning on the users' private data.  ... 
arXiv:2009.00155v3 fatcat:yqkew4n4q5gtbjosozufw37ome

Instance Hard Triplet Loss for In-video Person Re-identification

Xing Fan, Wei Jiang, Hao Luo, Weijie Mao, Hongyan Yu
2020 Applied Sciences  
Traditional Person Re-identification (ReID) methods mainly focus on cross-camera scenarios, while identifying a person in the same video/camera from adjacent subsequent frames is also an important question  ...  can extract multi-person features efficiently in real time and can be integrated with both one-stage and two-stage human or pose detectors.  ...  person re-identification.  ... 
doi:10.3390/app10062198 fatcat:bzcljukeyfac3pecibiyc7r66u

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier.  ...  This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers.  ...  The error rate rises to 8.7% for 4K persons with 4.4M images, showing the network scales comfortably to more persons.  ... 
doi:10.1109/cvpr.2014.220 dblp:conf/cvpr/TaigmanYRW14 fatcat:wcogawlivfbqtn27pwhxt4dcyq

Signal-Based Intelligent Hydraulic Fault Diagnosis Methods: Review and Prospects

Juying Dai, Jian Tang, Shuzhan Huang, Yangyang Wang
2019 Chinese Journal of Mechanical Engineering  
Based on deep learning, deep neural networks (DNNs) can automatically learn the complex nonlinear relations implied in a signal, can be globally optimized, and can obtain the high-level features of multi-dimensional  ...  Among them, signal-based methods are commonly used, which employ signal processing techniques based on the state signal used for extracting features, and further input the features into the classifier  ...  Acknowledgements The authors sincerely thanks to Professor Ting Rui of Army Engineering University for his critical discussion and reading during manuscript preparation.  ... 
doi:10.1186/s10033-019-0388-9 fatcat:lho5v4o7djhjbhfz2t33pd7as4

Intrinsic plasticity via natural gradient descent with application to drift compensation

K. Neumann, C. Strub, J.J. Steil
2013 Neurocomputing  
This paper investigates the learning dynamics of intrinsic plasticity (IP), which is a learning rule to tune a neuron's activation function such that its output distribution becomes approximately exponentially  ...  Together with a further new modification of the IP rule, the high capability of NIP to cope with drift is demonstrated to have superior performance as compared to the standard gradient in experiments with  ...  To the best of our knowledge, there is currently no other approach with these two features.  ... 
doi:10.1016/j.neucom.2012.12.047 fatcat:rqpa6tj7njcznpvhegcqaxkee4

A Survey on Machine Learning-Based Performance Improvement of Wireless Networks: PHY, MAC and Network Layer

Merima Kulin, Tarik Kazaz, Eli De Poorter, Ingrid Moerman
2021 Electronics  
This paper presents a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering  ...  all layers of the protocol stack: PHY, MAC and network.  ...  Recently, the authors of [172] proposed a novel accumulated polar feature based deep learning algorithm with a channel compensation mechanism for AMR that is capable to learn from A/Ph domain with historical  ... 
doi:10.3390/electronics10030318 fatcat:p6jslz26dvfvbpnqzmrpptloim

2020 Index IEEE Signal Processing Letters Vol. 27

2020 IEEE Signal Processing Letters  
., +, LSP 2020 2144-2148 Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification.  ...  Xu, J., Generated Data With Sparse Regularized Multi-Pseudo Label for Person Re-Identification; LSP 2020 391-395 Huang, M., Liu, Z., Li, G., Zhou, X., and Le Meur, O., FANet: Features Adaptation Network  ... 
doi:10.1109/lsp.2021.3055468 fatcat:wfdtkv6fmngihjdqultujzv4by

Machine Learning: A Software Process Reengineering in Software Development Organization

2019 International Journal of Engineering and Advanced Technology  
Machine Learning (ML) can be the key aspect for BPR in software development organization.  ...  BPR (Business Process Re-engineering) is an organizational mechanism that improves the organizational ability in responding to the challenges of qualitative result by change management and improvement  ...  For example, to select specific features to train an algorithm to detect an object requires specialized image processing knowledge.  ... 
doi:10.35940/ijeat.b4563.129219 fatcat:po2gmgfqw5e4vphjhwiws5kkka

Artificial Intelligence Methodologies for Data Management

Joel Serey, Luis Quezada, Miguel Alfaro, Guillermo Fuertes, Manuel Vargas, Rodrigo Ternero, Jorge Sabattin, Claudia Duran, Sebastian Gutierrez
2021 Symmetry  
Furthermore, the artificial intelligence methods with more symmetry in all groups are artificial neural networks, Support Vector Machines, K-means, and Bayesian Methods.  ...  The study of data management using AI methodologies presents symmetry in the four machine learning groups: supervised learning, unsupervised learning, semi-supervised learning, and reinforced learning.  ...  Facial recognition Person re-identification Classification/Research article [143] Improved prediction rate and time ANN Image and video Robust hierarchical tracker Classification/Research article [144  ... 
doi:10.3390/sym13112040 fatcat:dtcfzqmka5byxhupaennbb77xi

Use of Transfer Learning for Automatic Dietary Monitoring through Throat Microphone Recordings

Mehmet Ali Tugtekin Turan, Engin Erzin
2019 Zenodo  
We propose a new domain adaptation framework in a heterogeneous setup based on T/S learning paradigm.  ...  Recently, the teacher/student (T/S) learning paradigm is introduced as a model compression framework, where it describes a class of learning methods for training a smaller student network by mimicking  ...  Convolutional Neural Networks (CNNs) The CNN is considered as a modified version of the standard feed-forward neural network with some structural differences, which provide unsupervised feature learning  ... 
doi:10.5281/zenodo.3841957 fatcat:so4kiaj4ljbw5aay36xd6dlx2q

MineRank: Leveraging users' latent roles for unsupervised collaborative information retrieval

Laure Soulier, Lynda Tamine, Chirag Shah
2016 Information Processing & Management  
In this article, we propose a new unsupervised collaborative ranking algorithm which leverages collaborators' actions for (1) mining their latent roles in order to extract their complementary search behaviors  ...  Experiments using two user studies with respectively 25 and 10 pairs of collaborators demonstrate the benefit of such an unsupervised method driven by collaborators' behaviors throughout the search session  ...  in which feature weight is depreciated, and the current maximum clique.  ... 
doi:10.1016/j.ipm.2016.05.002 fatcat:5qi74lgxdff7thntnaijxdvphu

Use of Transfer Learning for Automatic Dietary Monitoring through Throat Microphone Recordings

Mehmet Ali Tugtekin Turan, Engin Erzin
2019 Zenodo  
We propose a new domain adaptation framework in a heterogeneous setup based on T/S learning paradigm.  ...  Recently, the teacher/student (T/S) learning paradigm is introduced as a model compression framework, where it describes a class of learning methods for training a smaller student network by mimicking  ...  Convolutional Neural Networks (CNNs) The CNN is considered as a modified version of the standard feed-forward neural network with some structural differences, which provide unsupervised feature learning  ... 
doi:10.5281/zenodo.3841956 fatcat:ncalroecszg3hhpc45havcxhee

Neural Networks in Big Data and Web Search

Will Serrano
2018 Data  
Finally, the random neural network is presented with its practical applications to reasoning approaches for knowledge extraction.  ...  The use of artificial intelligence (AI) based on neural networks and deep learning in learning relevance and ranking is also analyzed, including its utilization in Big Data analysis and semantic applications  ...  An adaptive resonance theory (ART) is an unsupervised learning method based on a neural network, comprised of a comparative and an identification layer both formed of neurons.  ... 
doi:10.3390/data4010007 fatcat:2irxpdvtfrclrbndkrubl5jvqq

Model-Based Deep Learning [article]

Nir Shlezinger, Jay Whang, Yonina C. Eldar, Alexandros G. Dimakis
2021 arXiv   pre-print
Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data.  ...  Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance, especially for supervised problems.  ...  iterative algorithm with the same model-mismatch, as the unfolded network can learn to compensate for this mismatch [56] .  ... 
arXiv:2012.08405v2 fatcat:4ilqi3vv4rar5gsveqzo4loqpy

Intelligence at the Extreme Edge: A Survey on Reformable TinyML [article]

Visal Rajapakse, Ishan Karunanayake, Nadeem Ahmed
2022 arXiv   pre-print
In this work, we present a survey on reformable TinyML solutions with the proposal of a novel taxonomy for ease of separation.  ...  The rapid miniaturization of Machine Learning (ML) for low powered processing has opened gateways to provide cognition at the extreme edge (E.g., sensors and actuators).  ...  However, with no requirement for a knowledge base, these techniques can learn from a limitless quantity of data.  ... 
arXiv:2204.00827v1 fatcat:6wgnjixzvrdg7hfllxyajestra
« Previous Showing results 1 — 15 out of 1,555 results