Filters








2,587 Hits in 5.7 sec

Gaussian process decentralized data fusion meets transfer learning in large-scale distributed cooperative perception

Ruofei Ouyang, Bryan Kian Hsiang Low
2019 Autonomous Robots  
and Procedural Tasks Aaron Mininger*, John Laird Interpretable Graph-Based Semi-Supervised Learning via Flows Raif Rustamov*, James Klosowski Interpreting CNN Knowledge Via An Explanatory Graph Quanshi  ...  Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition Yang Du, Chunfeng Yuan*, Weiming Hu, Hao Yang Hierarchical Policy Search via Return-Weighted  ... 
doi:10.1007/s10514-018-09826-z fatcat:67yqhwmgozccxni56rxmuapjgm

Towards Robust Pattern Recognition: A Review [article]

Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen
2020 arXiv   pre-print
Actually, our brain is robust at learning concepts continually and incrementally, in complex, open and changing environments, with different contexts, modalities and tasks, by showing only a few examples  ...  The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance.  ...  [318] , traffic sign recognition [177] , autonomous driving [44] , emotion recognition [38] , and so on.  ... 
arXiv:2006.06976v1 fatcat:mn35i7bmhngl5hxr3vukdcmmde

Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation [article]

Lin Wang, Yujeong Chae, Kuk-Jin Yoon
2021 arXiv   pre-print
It has been shown that events alone can be used for end-task learning, e.g., semantic segmentation, based on encoder-decoder-like networks.  ...  The proposed approach consists of three parts: event to end-task learning (EEL) branch, event to image translation (EIT) branch, and transfer learning (TL) module that simultaneously explores the feature-level  ...  Multi-task learning.  ... 
arXiv:2109.01801v3 fatcat:hvbsry4t7rgxblyb677siqzkcu

Investigations of Object Detection in Images/Videos Using Various Deep Learning Techniques and Embedded Platforms—A Comprehensive Review

Chinthakindi Balaram Murthy, Mohammad Farukh Hashmi, Neeraj Dhanraj Bokde, Zong Woo Geem
2020 Applied Sciences  
This paper shows a detailed survey on recent advancements and achievements in object detection using various deep learning techniques.  ...  From 2012 onward, deep learning-based techniques were used for feature extraction, and that led to remarkable breakthroughs in this area.  ...  [205] multi-task CNN to recognize all traffic signs classes which include both symbol-based and text-based signs. Li et al.  ... 
doi:10.3390/app10093280 fatcat:e6jrltv6lrhxjntlhq7d34247e

Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations [article]

Rohan Paleja, Andrew Silva, Letian Chen, Matthew Gombolay
2021 arXiv   pre-print
We propose a personalized and interpretable apprenticeship scheduling algorithm that infers an interpretable representation of all human task demonstrators by extracting decision-making criteria via an  ...  inferred, personalized embedding non-parametric in the number of demonstrator types.  ...  Learning a multi-modal policy via imitating demonstrations with mixed behaviors.  ... 
arXiv:1906.06397v5 fatcat:thqmemuqjzcpdifn36zow4n6he

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Emerging Relation Network and Task Embedding for Multi-Task Regression Problems.pdf Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game.  ...  DAY 2 -Jan 13, 2021 Chen, Zhuo; Yin, Fei; Zhang, Xu- Yao; Yang, Qing; Liu, Cheng-Lin 953 Cross-Lingual Text Image Recognition Via Multi-Task Sequence to Sequence Learning DAY 2 -Jan 13, 2021  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

IEEE Access Special Section Editorial: AI-Driven Big Data Processing: Theory, Methodology, and Applications

Zhanyu Ma, Sunwoo Kim, Pascual Martinez-Gomez, Jalil Taghia, Yi-Zhe Song, Huiji Gao
2020 IEEE Access  
Multi-task learning (MTL) is a machine learning method to share knowledge for multiple related machine learning tasks via learning those tasks jointly.  ...  The article by Sun et al., ''Common knowledge based and one-shot learning enabled multi-task traffic classification,'' proposes a multi-output DNN model to simultaneously learn multi-task traffic classifications  ...  In the article ''An artificial intelligence driven multi-feature extraction scheme  ... 
doi:10.1109/access.2020.3035461 fatcat:rt7ejtponrfexigie4cfpt7gd4

2020 Index IEEE Transactions on Intelligent Transportation Systems Vol. 21

2020 IEEE transactions on intelligent transportation systems (Print)  
., +, TITS Jan. 2020 79-86 Deep Learning for Large-Scale Traffic-Sign Detection and Recognition.  ...  Zheng, Y., +, TITS Nov. 2020 4605-4614 Deep Learning for Large-Scale Traffic-Sign Detection and Recognition.  ... 
doi:10.1109/tits.2020.3048827 fatcat:ab6he3jkfjboxg7wa6pagbggs4

Empowering Real-Time Traffic Reporting Systems With NLP-Processed Social Media Data

Xiangpeng Wan, Michael C. Lucic, Hakim Ghazzai, Yehia Massoud
2020 IEEE Open Journal of Intelligent Transportation Systems  
Along with these wellleveraged data streams, drivers and passengers tend to report traffic information to social media platforms.  ...  In this paper, we develop an automated Natural Language Processing (NLP)-based framework to empower and complement traffic reporting solutions by text mining social media, extracting desired information  ...  It has been shown that the BERT model is achieving extraordinary performance in many tasks such as named entity recognition and question answering via transfer learning.  ... 
doi:10.1109/ojits.2020.3024245 fatcat:ozfckwdpurc7xb4csch532ntjy

Derin Öğrenme Araştırma Alanlarının Literatür Taraması

M. Mutlu Yapıcı, Adem Tekerek, Nurettin Topaloğlu
2019 Gazi Mühendislik Bilimleri Dergisi  
In the present day, Deep learning methods have reached better results than humans in object recognition.  ...  Derin öğrenme (Deep Learning-DL), birçok alanda önemli başarılar elde etmiş güçlü bir makine öğrenmesi yöntemidir.  ...  [25] first construct deep CNN layers for color and depth separately, which are then connected with a designed multi-modal learning framework for RGB-D object recognition. Zhang et al.  ... 
doi:10.30855/gmbd.2019.03.01 fatcat:2sv7dg7elrfqppcjx5otzmb7pi

Data Analytics in the Internet of Things: A Survey

Tausifa Jan Saleem, Mohammad Ahsan Chishti
2019 Scalable Computing : Practice and Experience  
Learning/ DBN To detect android malwares in smart phone Android applica- tions Accuracy: 96 percent [84] Traffic sign detection Deep Learning/ CNN To detect traffic signs - - [85]  ...  unstructured nature as well, (iii) data sources are diverse and fully distributed, and (iv) integration of multi-modal data becomes complex.  ... 
doi:10.12694/scpe.v20i4.1562 fatcat:y2fiya3q2bawhdg6hhczfpdbee

A Survey on Multi-Task Learning [article]

Yu Zhang, Qiang Yang
2018 arXiv   pre-print
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of  ...  learning, multi-view learning and graphical models.  ...  A multi-task model with a tree-structured regularization and the 2,1 regularization is proposed in [214] to recognition traffic signs.  ... 
arXiv:1707.08114v2 fatcat:6lrpe4nk45djbjyfjco7t4yfme

Learning Deep and Wide: A Spectral Method for Learning Deep Networks

Ling Shao, Di Wu, Xuelong Li
2014 IEEE Transactions on Neural Networks and Learning Systems  
The one-shot-learning scenario for gesture recognition is also studied. The Multi-view Spectral Embedding is proposed to fuse the information from RGB and depth images.  ...  Neural Networks [14] achieve near-human performance on the handwritten digits and traffic signs recognition benchmarks; 3D Convolutional Neural Networks [15, 16] recognize human actions in surveillance  ...  from RGBD Images The Matlab code for generating "One Shot Learning Gesture Recognition from RGBD Images" for section 2.3 can be found at: https://github.com/stevenwudi/Kaggle_one_shot_learning Matlab  ... 
doi:10.1109/tnnls.2014.2308519 pmid:25420251 fatcat:4mnl6tv2xnf3jpzwhp76cvl4ti

CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network [article]

Yanlin Wang, Ensheng Shi, Lun Du, Xiaodi Yang, Yuxuan Hu, Shi Han, Hongyu Zhang, Dongmei Zhang
2021 arXiv   pre-print
Then, relevant Unified Modeling Language (UML) class diagrams are extracted as inter-class context and are encoded into the class relational embeddings using a novel Multi-Relational Graph Neural Network  ...  Class semantic embeddings and class relational embeddings, together with the outputs from code token encoder and AST encoder, are passed to a decoder armed with a two-level attention mechanism to generate  ...  Graph Neural Networks The recent advances of deep learning techniques have facilitated many machine learning tasks like object detection, machine translation, and speech recognition ].  ... 
arXiv:2107.01933v1 fatcat:g4mdjrdpszf2xnwjq32quc3mna

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
Fulfilling these tasks is challenging, as mobile environments are increasingly complex, heterogeneous, and evolving.  ...  Upcoming 5G systems are evolving to support exploding mobile traffic volumes, agile management of network resource to maximize user experience, and extraction of fine-grained real-time analytics.  ...  [535] Multi-task multi-agent reinforcement learning under partial observability.  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde
« Previous Showing results 1 — 15 out of 2,587 results