Filters








131,771 Hits in 4.6 sec

A metric approach toward point process divergence

Sohan Seth, Austin J. Brockmeier, Jose C. Principe
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Since the space of spike trains can be viewed as a metric space, we address the problem of estimating Jensen-Shannon divergence in a metric space using a nearest neighbor based approach.  ...  Estimating divergence between two point processes, i.e. probability laws on the space of spike trains, is an essential tool in many computational neuroscience applications, such as change detection and  ...  divergence between two point processes.  ... 
doi:10.1109/icassp.2011.5946741 dblp:conf/icassp/SethBP11 fatcat:mis2c5bq5rhr7azcewxegw3ou4

Review of the AMLAS Methodology for Application in Healthcare [article]

Shakir Laher, Carla Brackstone, Sara Reis, An Nguyen, Sean White, Ibrahim Habli
2022 arXiv   pre-print
As the frameworks are in the process of reformation, there is a need to proactively assure the safety of ML to prevent patient safety being compromised.  ...  This review has appraised the methodology by consulting ML manufacturers to understand if it converges or diverges from their current safety assurance practices, whether there are gaps and limitations  ...  This approach ensured discussions focused on those salient points which needed exploration.  ... 
arXiv:2209.00421v1 fatcat:zqbjx7jqvvhtroa5n5knvjpnxa

Benchmarking and Functional Decomposition of Automotive Lidar Sensor Models

Philipp Rosenberger, Martin Holder, Sebastian Hueh, Hermann Winner, Tobias Fleek, Marc Rene Zofka, J. Marius Zollner, Thomas D'hondt, Benjamin Wassermann
2019 2019 IEEE Intelligent Vehicles Symposium (IV)  
Subsequently, metrics applied to the aforementioned interfaces are derived, enabling a quantitative comparison between simulated and real sensor data at different steps of the processing pipeline.  ...  Currently, an objective evaluation and the comparison of different modeling approaches for automotive lidar sensors are still a challenge.  ...  Nevertheless, most metrics on IF2 do work on IF1, as well. A. Metrics on point cloud interface (IF2) There are multiple metrics for comparing point clouds as described in [23] .  ... 
doi:10.1109/ivs.2019.8814081 dblp:conf/ivs/RosenbergerHHWF19 fatcat:pv5m2wfvhnctvoeovpvkpm3ige

Deep Divergence Learning [article]

Kubra Cilingir, Rachel Manzelli, Brian Kulis
2020 arXiv   pre-print
existing deep metric learning approaches.  ...  learning approaches for extending learning Euclidean distances to more general divergence measures such as divergences over distributions.  ...  Figure 1 gives a high-level overview of our approach, which we term as deep Bregman divergences, in comparison to existing metric learning approaches.  ... 
arXiv:2005.02612v1 fatcat:d4zwdlkw5ffnbjbx776jpikgou

Recent trends in computational intelligence in life sciences

Udo Seiffert, Frank-Michael Schleif, Dietlind Zühlke
2011 The European Symposium on Artificial Neural Networks  
Computational intelligence generally comprises a rather large set of -in a wider sense -adaptive and human-like data analysis and modelling methods.  ...  A very prominent field among them are life sciences that are characterised by some unique requirements in terms of data structure and analysis.  ...  A more general approach is to consider an abstract space where common divergences, such as Kullback-Leibler-, Csiszár-Morimoto-, or Bregman-divergence can be generalised towards Alpha-, Beta-, and Gamma-divergences  ... 
dblp:conf/esann/SeiffertSZ11 fatcat:s2id3os5fnatbomperpzl24uzm

Metric Gaussian Variational Inference [article]

Jakob Knollmüller, Torsten A. Enßlin
2020 arXiv   pre-print
We propose Metric Gaussian Variational Inference (MGVI) as a method that goes beyond mean-field.  ...  We alternate between approximating the covariance with the inverse Fisher information metric evaluated at an intermediate mean estimate and optimizing the KL-divergence for the given covariance with respect  ...  At a some point towards smaller scales the uncertainty increases significantly. This is also the point where the recovered spectrum diverges from the true one.  ... 
arXiv:1901.11033v3 fatcat:4xth43f4mzaanir4rwr5hufq2i

Autonomous navigation and mapping using monocular low-resolution grayscale vision

Vidya N. Murali, Stanley T. Birchfield
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
Turning at the end of a corridor is accomplished using Jeffrey divergence and time-to-collision, while deflection from dead ends and blank walls uses a scalar entropy measure of the entire image.  ...  The robot can autonomously explore an unknown indoor environment, recovering from difficult situations like corners, blank walls, and initial heading toward a wall.  ...  In some systems, lights are used as landmarks in a teach/replay approach, with the camera pointing toward the ceiling [23] .  ... 
doi:10.1109/cvprw.2008.4563136 dblp:conf/cvpr/MuraliB08 fatcat:qwtw4etyvjgh3pel47vsvr2gpm

A Case for Quantifying Statistical Robustness of Specialized Probabilistic AI Accelerators [article]

Xiangyu Zhang, Sayan Mukherjee, Alvin R. Lebeck
2020 arXiv   pre-print
Although a common approach is to compare the end-point result quality using community-standard benchmarks and metrics, we claim a probabilistic architecture should provide some measure (or guarantee) of  ...  This work takes a first step towards quantifying the statistical robustness of specialized hardware MCMC accelerators by proposing three pillars of statistical robustness: sampling quality, convergence  ...  A common approach is to compare the endpoint result quality using community-standard benchmarks and metrics, such as accuracy in classification, end-point error in optical flow, and bad-pixel percentage  ... 
arXiv:1910.12346v2 fatcat:w5pt6ssn6vaqlhaab373c5l4xi

Quantifying the limited and gradual concept drift assumption

Joseph Sarnelle, Anthony Sanchez, Robert Capo, Joshua Haas, Robi Polikar
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
We test these metrics on both synthetic and real world problems, and argue that the latter can be more suitably used. 978-1-4799-1959-8/15/$31.00 c O2015 IEEE  ...  We define two metrics, one that represents the normalized class separation drift, and the other that uses the ratio of betweenclass separations and within class drift through time.  ...  The DCR value approaches 1 only when a class is drifting towards the core support of another class, but remains far below 1 when drifting away from it.  ... 
doi:10.1109/ijcnn.2015.7280850 dblp:conf/ijcnn/SarnelleSCHP15 fatcat:22otz3aokbc7djamlivkzg7eii

Abstracts of the LIX Fall Colloquium 2008: Emerging Trends in Visual Computing [chapter]

Frank Nielsen
2009 Lecture Notes in Computer Science  
In most instances, the original scanner data is just a set, but a very large set, of points sampled from the surface of the object.  ...  This talk will present a number of point-based techniques for discovering global structure in 3D data sets, including partial and approximate symmetries, shared parts, repeated patterns, etc.  ...  The manifold possesses a Riemannian metric, two types of geodesics, and a divergence function.  ... 
doi:10.1007/978-3-642-00826-9_1 fatcat:7ppk5awzqrhexlrcvbon24qr7m

A Minimal-Sensing Framework for Monitoring Multistage Manufacturing Processes Using Product Quality Measurements

Hossein Davari Ardakani, Jay Lee
2018 Machines  
A moving window is applied to the data, and a statistical metric is extracted by comparing the performance of a machine to its peers. This approach is expanded to work for multistage processes.  ...  The proposed method is validated using a dataset from a real-world manufacturing process and additional simulated datasets.  ...  However, it can be considered a viable approach for quantifying the divergence of machines in a manufacturing process.  ... 
doi:10.3390/machines6010001 fatcat:tdaajtahqzcmlhdzg5auic3srm

How to Identify Boundary Conditions with Contrasty Metric? [article]

Weilin Luo and Hai Wan and Xiaotong Song and Binhao Yang and Hongzhen Zhong and Yin Chen
2021 arXiv   pre-print
Then we design a post-processing framework (PPAc) to produce a set of contrastive BCs after identifying BCs.  ...  Unfortunately, a large number of identified BCs make assessing and resolving divergences expensive. Existing methods adopt a coarse-grained metric, generality, to filter out less general BCs.  ...  The contrasty metric mainly distinguishes the difference between BCs from the point of resolving divergences.  ... 
arXiv:2103.02384v1 fatcat:mwtnywb7yzbxrg75gkkn2wcdrm

Page 116 of Astronomy and Astrophysics Vol. 326, Issue 1 [page]

1997 Astronomy and Astrophysics  
= a;; —_- —_ ) dt dt for particles of unit mass. Here the a;; are elements of the metric tensor and 6, refers to variations in the trajectory 7 holding the energy and the end points fixed.  ...  One drawback of such an approach, however, is that one is compar- ing the divergence in phase-space of different temporal states and not trajectories.  ... 

Metrics for Performance Evaluation of Patient Exercises during Physical Therapy

Aleksandar Vakanski, Jake M Ferguson, Stephen Lee
2017 International Journal of Physical Medicine & Rehabilitation  
Results: The metrics are evaluated for a set of five human motions captured with a Kinect sensor.  ...  The reviewed metrics include root-mean square distance, Kullback Leibler divergence, log-likelihood, heuristic consistency, Fugl-Meyer Assessment, and similar.  ...  While the quantitative metrics evaluate the motions at a low level of abstraction, i.e., at a level of individual measurement points in a sequence, the qualitative metrics evaluate the motions at a high  ... 
doi:10.4172/2329-9096.1000403 pmid:28752104 pmcid:PMC5526359 fatcat:fjj7inyrwfal5anq74y37aq4ya

Towards precision holography [article]

Niko Jokela, Arttu Pönni
2020 arXiv   pre-print
Our approach therefore opens up a novel gateway for precision holography.  ...  We present a statistical approach to bulk reconstruction from entanglement entropy measurements, which handles the presence of noise in a natural way.  ...  Acknowledgments We thank Carlos Hoyos and Esko Keski-Vakkuri for useful discussions and comments on a draft version of the article.  ... 
arXiv:2007.00010v1 fatcat:rfurqmbcffcgzfiwsmwo4czbeq
« Previous Showing results 1 — 15 out of 131,771 results