A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Manifold for Machine Learning Assurance
[article]
2020
pre-print
The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. ...
--a manifold. ...
INTRODUCTION Machine-learning enabled systems are being increasingly adopted in safety-critical applications. ...
doi:10.1145/3377816.3381734
arXiv:2002.03147v1
fatcat:l2bmc2cwrbalrkehwielxmgktu
Deep Learning and Machine Learning in Robotics [From the Guest Editors]
2020
IEEE robotics & automation magazine
of machine/deep learn ing systems. ...
The article then illustrates the use of Gaussians on Rie mannian manifolds for movement gen eration in more detail. ...
doi:10.1109/mra.2020.2984470
fatcat:jpzcc556kbftne5nrjhjbdthsq
Hybrid intelligent algorithms and applications
2010
Information Sciences
Most of these techniques are evolved from fields such as statistics, machine learning, artificial intelligence, and pattern recognition. ...
The topic of dimensionality reduction and manifold learning has recently attracted a great deal of attention with a number of advanced techniques being proposed. ...
Network for Innovation and Research Excellence,
USA
E-Ajith Abraham
Machine Intelligence Research Labs (MIR Labs),
Scientific Network for Innovation and Research Excellence,
USA
E-mail address: ...
doi:10.1016/j.ins.2010.02.019
fatcat:tvxp7ok7czedblym4mcsteibw4
Reactive Whole-Body Obstacle Avoidance for Collision-Free Human-Robot Interaction with Topological Manifold Learning
[article]
2022
arXiv
pre-print
Unlike existing Jacobian-type or geometric approaches, our proposed methodology leverages both topological manifold learning and latest deep learning advances, therefore can not only be readily generalized ...
Unfortunately, for most robotic systems, their shared working environment with human operators may not always be static, instead often dynamically varying and being constantly cluttered with unanticipated ...
feedback for dynamically re-planning to assure safe trajectory. ...
arXiv:2203.13821v1
fatcat:4v2hg6stbvdp7ebznvysj5p3ue
Quantum Annealing for Semi-Supervised Learning
[article]
2020
arXiv
pre-print
Semi-supervised learning is a machine learning technique that makes use of both labeled and unlabeled data for training, which enables a good classifier with only a small amount of labeled data. ...
In this paper, we propose and theoretically analyze a graph-based semi-supervised learning method with the aid of the quantum annealing technique, which efficiently utilize the quantum resources while ...
For instance, the quantum version of linear models of machine learning, such as support vector machines (SVM) [8] , principal component analysis (PCA) [9] , can be potentially more efficient than their ...
arXiv:2003.12459v2
fatcat:ho6q5tw6zrb7xo7n4y73fth7re
Density-Based LLE Algorithm for Network Forensics Data
2011
International Journal of Modern Education and Computer Science
II MANIFOLD LEARNING AND KDDCUP'99 DATA SET A. ...
In this paper, a schema is proposed to reduce the data of the forensics using manifold learning. Manifold learning is a popular recent approach to nonlinear dimensionality reduction. ...
V FUTURE WORK Manifold learning is a good way to reduce the dimensional, especially, the manifold learning can maintain the topology of the data set, which can supply rich information for the data clustering ...
doi:10.5815/ijmecs.2011.01.08
fatcat:2diwnjsemrhx7bytgkaoekuzni
Guest Editorial: Special Section on Advanced Signal Processing and AI Technologies for Industrial Big Data
2021
IEEE Transactions on Industrial Informatics
SUMMARIES OF ACCEPTED ARTICLES The first article "Support Multi-Mode Tensor Machine for Multiple Classification on Industrial Big Data," authored by Ma et al., presents a support multimode tensor machine ...
learning for digital signal processing of industrial inspection applications. ...
doi:10.1109/tii.2020.3034627
fatcat:6kup2ffijvgi3mdpm6qdzo6l4a
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
[article]
2020
arXiv
pre-print
Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. ...
Several defenses for adversarial examples exist in the literature. ...
Introduction to semi-supervised learning. Synthesis Lectures
on Artificial Intelligence and Machine Learning, 3(1):1-130, 2009. ...
arXiv:1909.03334v4
fatcat:dc6vzg2u6benjkszw6nn6qm5ti
Page 01 of Collier's: The National Weekly Vol. 36, Issue 2
[page]
1905
Collier's: The National Weekly
.,
manifolding power, speed, compare with any or all of the well known and widely advertised typewriters, and if you are not assured that you have in the Burnett the equal and in fact the superior of any ...
OUR BURNETT TYPEWRITER Soand the same as is used on
BOARD, the same as is used on all the widely sold machines, so that anyone who has learned to operate any of the standard machines wil! ...
Machine learning CICY threefolds
2018
Physics Letters B
learned. ...
The latest techniques from Neural Networks and Support Vector Machines (SVM) are used to investigate geometric properties of Complete Intersection Calabi-Yau (CICY) threefolds, a class of manifolds that ...
We thank participants at the "Tsinghua Workshop on Machine Learning in Geometry and Physics 2018" for comments. ...
doi:10.1016/j.physletb.2018.08.008
fatcat:ceyqxotusnebxcyxtgdgptwt54
Page 34 of Manufacturing Engineering Vol. 7, Issue 1
[page]
1938
Manufacturing Engineering
Dickett’s many friends will be grieved to learn of his great loss and will join us in our feeling of sympathy for him. ...
The new system, as arranged in Fig. 2, meets every requirement for this type of lubrication, assures delivery of oil to all moving parts, makes it possible to use a filter and pump of reasonable size, ...
Neural Networks with Manifold Learning for Diabetic Retinopathy Detection
[article]
2016
arXiv
pre-print
Computer-aided diagnosis of retinal images have recently gained increasing attention in the machine learning community. ...
In this paper, we introduce a set of neural networks for diabetic retinopathy classification of fundus retinal images. ...
Data Augmentation
Manifold Learning Manifold learning is a non-linear dimensionality reduction technique that is often applied in large scale machine learning models to address the curse of dimensionality ...
arXiv:1612.03961v1
fatcat:3qk65gbz6bh4lp37a642h67z6i
An Evaluation of Supervised Dimensionality Reduction For Large Scale Data
2022
Journal of Machine and Computing
Experimenters today frequently quantify millions or even billions of characteristics (measurements) each sample to address critical biological issues, in the hopes that machine learning tools would be ...
This research presents an evaluation of supervised dimensionality reduction for large scale data. ...
As for supervised learning, the non-linear manifold learning techniques learn mappings from the source data to environments that are of low-dimension but not projections showcasing that novel dataset cannot ...
doi:10.53759/7669/jmc202202003
fatcat:5uygro7p4rbb7cfhgr7nvdkp4m
Human Action Recognition Based on Random Spectral Regression
[chapter]
2011
Lecture Notes in Computer Science
For solving the uncertain parameter selection, the highly spatiotemporal complexity and the difficulty of effectively extracting feature in manifold learning algorithm processing higher-dimension of human ...
This method overcomes the neighborhood parameter selection of the manifold learning algorithm. ...
The authors would like to thank the anonymous reviewers for their insightful comments, which have helped to improve the quality of this paper. ...
doi:10.1007/978-3-642-23896-3_56
fatcat:ooghzci4mzasljmafyrep6xzxa
Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
[article]
2022
arXiv
pre-print
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. ...
We find that the geometry of the data sub-manifold is an important factor in determining the success of various models. ...
data via uncertainty is generally assured. ...
arXiv:2208.01705v1
fatcat:6jlryjlxmjgobkiotv6w7tmh6i
« Previous
Showing results 1 — 15 out of 10,769 results