1,181 resources related to Semisupervised learning
- Topics related to Semisupervised learning
- IEEE Organizations related to Semisupervised learning
- Conferences related to Semisupervised learning
- Periodicals related to Semisupervised learning
- Most published Xplore authors for Semisupervised learning
2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.
The International Conference on Image Processing (ICIP), sponsored by the IEEE SignalProcessing Society, is the premier forum for the presentation of technological advances andresearch results in the fields of theoretical, experimental, and applied image and videoprocessing. ICIP 2020, the 27th in the series that has been held annually since 1994, bringstogether leading engineers and scientists in image and video processing from around the world.
The 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2020) will be held in Metro Toronto Convention Centre (MTCC), Toronto, Ontario, Canada. SMC 2020 is the flagship conference of the IEEE Systems, Man, and Cybernetics Society. It provides an international forum for researchers and practitioners to report most recent innovations and developments, summarize state-of-the-art, and exchange ideas and advances in all aspects of systems science and engineering, human machine systems, and cybernetics. Advances in these fields have increasing importance in the creation of intelligent environments involving technologies interacting with humans to provide an enriching experience and thereby improve quality of life. Papers related to the conference theme are solicited, including theories, methodologies, and emerging applications. Contributions to theory and practice, including but not limited to the following technical areas, are invited.
The ICASSP meeting is the world's largest and most comprehensive technical conference focused on signal processing and its applications. The conference will feature world-class speakers, tutorials, exhibits, and over 50 lecture and poster sessions.
All fields of satellite, airborne and ground remote sensing.
Broad coverage of concepts and methods of the physical and engineering sciences applied in biology and medicine, ranging from formalized mathematical theory through experimental science and technological development to practical clinical applications.
Video A/D and D/A, display technology, image analysis and processing, video signal characterization and representation, video compression techniques and signal processing, multidimensional filters and transforms, analog video signal processing, neural networks for video applications, nonlinear video signal processing, video storage and retrieval, computer vision, packet video, high-speed real-time circuits, VLSI architecture and implementation for video technology, multiprocessor systems--hardware and software-- ...
Specific topics of interest include, but are not limited to, sequence analysis, comparison and alignment methods; motif, gene and signal recognition; molecular evolution; phylogenetics and phylogenomics; determination or prediction of the structure of RNA and Protein in two and three dimensions; DNA twisting and folding; gene expression and gene regulatory networks; deduction of metabolic pathways; micro-array design and analysis; proteomics; ...
The purpose of TDSC is to publish papers in dependability and security, including the joint consideration of these issues and their interplay with system performance. These areas include but are not limited to: System Design: architecture for secure and fault-tolerant systems; trusted/survivable computing; intrusion and error tolerance, detection and recovery; fault- and intrusion-tolerant middleware; firewall and network technologies; system management ...
Theory and application of fuzzy systems with emphasis on engineering systems and scientific applications. (6) (IEEE Guide for Authors) Representative applications areas include:fuzzy estimation, prediction and control; approximate reasoning; intelligent systems design; machine learning; image processing and machine vision;pattern recognition, fuzzy neurocomputing; electronic and photonic implementation; medical computing applications; robotics and motion control; constraint propagation and optimization; civil, chemical and ...
2009 International Conference on Communications, Circuits and Systems, 2009
In this paper, we proposed a novel semi-supervised classification method with path-based similarity measure for face recognition. Based on the manifold assumption, our method can reflect genuine similarities between data points on manifolds without any other additional knowledge, which takes into account the existence of noise and outliers in the face dataset. Comparison experiments between the proposed method and the ...
2008 IEEE International Conference on Data Mining Workshops, 2008
For multi-view learning, existing methods usually exploit originally provided features for classifier training, which ignore the latent correlation between different views. In this paper, semantic features integrating information from multiple views are extracted for pattern representation. Canonical correlation analysis is used to learn the representation of semantic spaces where semantic features are projections of original features on the basis vectors ...
2017 Third International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), 2017
Machine learning is widely used in various applications such as data mining, computer vision, and bioinformatics owing to the explosion of available data. However, in practice, many data have some missing attributes. The graphic theory serves as a powerful tool for modeling and analyzing many such practical problems, such as networks of communication and data organization. This paper focuses on ...
2008 Second International Conference on Future Generation Communication and Networking Symposia, 2008
Local Feature Extraction (LFE) algorithm is an effective feature extraction method developed in recent years. One of the shortcomings of the current LFE algorithm is that it can only process labeled data, and does not work well when the amount of the labeled data is limited. However, it is usually easy to obtain large amount of unlabeled data but only ...
2008 International Conference on Internet Computing in Science and Engineering, 2008
Model selection for semi-supervised support vector machine is an important step in a high-performance learning machine. It is usually done by minimizing an estimate of generalization error based on the bounds of the leave-one-out such as radius-margin bound and on the performance measures such as generalized approximate cross-validation empirical error, etc. In order to get the parameter of SVM with ...
Machine Learning of Motor Skills for Robotics
Linear Regression: Intro to Machine Learning Workshop - IEEE Region 4 Presentation
Overcoming the Static Learning Bottleneck - the Need for Adaptive Neural Learning - Craig Vineyard: 2016 International Conference on Rebooting Computing
Federated Learning for Networking - Anwar Walid - IEEE Sarnoff Symposium, 2019
Ensemble Approaches in Learning
Perception-Action-Learning and Associative Skill Memories
IEEE Day Future Milestone: Machine Learning in the future
ICASSP 2011 Trends in Machine Learning for Signal Processing
Signal Processing and Machine Learning
Continuously Learning Neuromorphic Systems with High Biological Realism: IEEE Rebooting Computing 2017
Learning with Memristive Neural Networks: Neuromorphic Computing - Joshua Yang at INC 2019
Brain-like Intelligence Inside - Towards Autonomously Interacting Systems
Panel Discussion - COVID-19, Deep Learning and Biomedical Imaging Panel
Deep Learning & Machine Learning Inference - Ashish Sirasao - LPIRC 2019
Computer-Assisted Audiovisual Language Learning
Learning Control and Knowledge Transfer Between Aerial Robots for Improved Accuracy in Trajectory Tracking
Data Modeling using Kernels and Information Theoretic Learning
ICRA 2020 Keynote - Can Deep Reinforcement Learning from pixels be made as efficient as from state?
2019 ICRA Plenary- Challenges for Deep learning towards AI
In this paper, we proposed a novel semi-supervised classification method with path-based similarity measure for face recognition. Based on the manifold assumption, our method can reflect genuine similarities between data points on manifolds without any other additional knowledge, which takes into account the existence of noise and outliers in the face dataset. Comparison experiments between the proposed method and the other two methods: PCA and LDA, are performed. The results show that the proposed method achieves the best face recognition.
For multi-view learning, existing methods usually exploit originally provided features for classifier training, which ignore the latent correlation between different views. In this paper, semantic features integrating information from multiple views are extracted for pattern representation. Canonical correlation analysis is used to learn the representation of semantic spaces where semantic features are projections of original features on the basis vectors of the spaces. We investigate the feasibility of semantic features on two learning paradigms: semi-supervised learning and active learning. Experiments on text classification with two state-of-the-art multi-view learning algorithms co- training and co-testing indicate that this use of semantic features can lead to a significant improvement of performance.
Machine learning is widely used in various applications such as data mining, computer vision, and bioinformatics owing to the explosion of available data. However, in practice, many data have some missing attributes. The graphic theory serves as a powerful tool for modeling and analyzing many such practical problems, such as networks of communication and data organization. This paper focuses on semi-supervised learning algorithms based on the graph theory, aiming at establishing robust models in the input space with a very limited number of training samples. The use of such algorithm in multiple data mining applications is also discussed.
Local Feature Extraction (LFE) algorithm is an effective feature extraction method developed in recent years. One of the shortcomings of the current LFE algorithm is that it can only process labeled data, and does not work well when the amount of the labeled data is limited. However, it is usually easy to obtain large amount of unlabeled data but only a few labeled data. In this paper, we propose a new feature extraction algorithm, called Semi-Supervised LFE (SSLFE), which can handle both labeled and unlabeled data to perform feature extraction. In the proposed algorithm, the labeled data are used to maximize the margin and the unlabeled data are used as regulations with respect to the intrinsic geometric structure of the data. The final projection matrix can be obtained by eigenvalue decomposition. Experiments on several datasets demonstrate that SSLFE achieves much higher classification accuracy than LFE.
Model selection for semi-supervised support vector machine is an important step in a high-performance learning machine. It is usually done by minimizing an estimate of generalization error based on the bounds of the leave-one-out such as radius-margin bound and on the performance measures such as generalized approximate cross-validation empirical error, etc. In order to get the parameter of SVM with RBF kernel, this paper presents a linear grid search method, which combines grid search and linear search. This method can reduce the resources required both in terms of processing time and of storage space. Experiments both on artificial and real word datasets show that the proposed linear grid search has the advantage of good performance compared to using linear search alone.
In order to classify tremendous amount of unlabeled samples accurately and efficiently, a land evaluation method based on semi-supervised learning algorithm is proposed in this paper. Extracting land evaluation association rules by training a small amount of labeled samples as the supervised information, combining with the Chameleon algorithm as the unsupervised method, the method clusters a great amount of unlabeled samples, which takes full advantage of high accuracy of supervised learning classification, reduces the complexity of clustering process, and improves the facility, interpretability and accuracy for the land evaluation model. Experimental results of Guangdong Province land resource demonstrate that, by only using 300 training samples chosen randomly, 94.4184% correct area rate of land evaluation could be obtained by the semi-supervised learning algorithm. It provides a higher precision with the accuracy improved by 4.9041%, comparing with the results of the method clustering in the same condition.
Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.
We consider the problem of labeling a partially labeled graph. This setting may arise in a number of situations from survey sampling to information retrieval to pattern recognition in manifold settings. It is also, especially, of potential practical importance when data is abundant, but labeling is expensive or requires human assistance. Our approach develops a framework for regularization on such graphs parallel to Tikhonov regularization on continuous spaces. The algorithms are very simple and involve solving a single, usually sparse, system of linear equations. Using the notion of algorithmic stability, we derive bounds on the generalization error and relate it to the structural invariants of the graph.
Mining data streams has attracted much attention recently. Labeled samples needed by most current stream classification methods are more difficult and expensive to obtain than unlabeled ones. This paper proposed a semi-supervised learning algorithm - clustering-training to utilize the unlabeled samples. It uses clustering to select confidently unlabeled samples, and uses them to re- train the classifier incrementally. Experiments on synthetic and real data set showed the effectiveness of the proposed algorithm
Recently, object tracking is viewed as a foreground/background two-class classification problem. In this paper, we propose a non-parameter approach to model the observation model for tracking via graph, which is a semi-supervised approach. More specially, the topology structure of graph is carefully designed to reflect the properties of the sample's distribution during tracking. In predication, the confidence of sample's label is propagation via random walk with restart (RWR), which can utilize labeled or unlabeled samples easily. The primary advantage of our algorithm is that it keeps the appearance of object in graph model, which can easily model the multi-modal of object appearance. Experimental results demonstrate that, compared with two state of the art methods, the proposed tracking algorithm is more effective, especially in dynamically changing and clutter scenes.
No standards are currently tagged "Semisupervised learning"
NLP Research Scientist / Engineer (ACL 2020)
AI/ML - Machine Learning Scientist, Siri Understanding
AI/ML - NLP Research Scientist, Siri Understanding
NLP Research Scientist / Engineer (SIGDIAL 2020)