Filters








8,213 Hits in 4.2 sec

Learning a Spatial Field in Minimum Time With a Team of Robots

Varun Suryan, Pratap Tokekar
2020 IEEE Transactions on robotics  
The disks are of radii 3r max which are concentric with disks of radii r max in I. The approximate optimal TSP tour visiting the centers is shown in blue.  ...  The mean was calculated over a set of grid locations inside the farm. 4.3 Disk placement covering the farm calculated by DC algorithm.  ...  We exploit the properties of squared-exponential kernel to find the measurement locations.  ... 
doi:10.1109/tro.2020.2994003 fatcat:hzezrf2xtzbqjhk5lfcfblsxzi

Exploiting Reflectional and Rotational Invariance in Single Image Superresolution

Simon Donn, Laurens Meeus, Hiep Quang Luong, Bart Goossens, Wilfried Philips
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Stationarity of reconstruction problems is the crux to enabling convolutional neural networks for many image processing tasks: the output estimate for a pixel is generally not dependent on its location  ...  We show how it can be applied to SRCNN and FSRCNN both, speeding up convergence in the initial training phase, and improving performance both for pretrained weights and after finetuning 1 .  ...  Instead, they raise scale invariance: image self-similarity means that information from multiple scales can be exploited during reconstruction.  ... 
doi:10.1109/cvprw.2017.141 dblp:conf/cvpr/DonneMLGP17 fatcat:5wgid6ajava4dgpu7haptz3wwi

Structural Learning in a Visuomotor Adaptation Task Is Explicitly Accessible

Krista M. Bond, Jordan A. Taylor
2017 eNeuro  
Implicit learning offered little to no contribution.  ...  We found that participants who experienced congruent training and test phase structure (i.e., rotations to rotation) learned more quickly than participants exposed to incongruent training and test phase  ...  Likewise, when participants experience rotational perturbations, they learn to exploit the off-diagonal terms of the rotation matrix.  ... 
doi:10.1523/eneuro.0122-17.2017 pmid:28856241 pmcid:PMC5572440 fatcat:ctv3hkmdgjacnhopk564wugfve

Using GPS to learn significant locations and predict movement across multiple users

Daniel Ashbrook, Thad Starner
2003 Personal and Ubiquitous Computing  
We present a system that automatically clusters GPS data taken over an extended period of time into meaningful locations at multiple scales.  ...  Location is the most common form of context used by these agents to determine the user's task.  ...  Thanks to Graham Coleman for writing visualization tools and to MapBlast (http://www.mapblast.com) for having freely available maps.  ... 
doi:10.1007/s00779-003-0240-0 fatcat:jy52vsge2nf33e2jp2l42xf77m

Learning a Spatial Field in Minimum Time with a Team of Robots [article]

Varun Suryan, Pratap Tokekar
2020 arXiv   pre-print
We study an informative path-planning problem where the goal is to minimize the time required to learn a spatially varying entity.  ...  We also study a multi-robot version where the objective is to minimize the time required by the last robot to return to a common starting location called depot.  ...  Multiple observations at a location is equivalent to that location being counted as many times as the number of measurements.  ... 
arXiv:1909.01895v2 fatcat:c27nqqyamzaqxbrvpruojdsjee

Exploiting Implicit Kinematic Kernel for Controlling a Wearable Robotic Extra-finger [article]

Tommaso Lisini Baldi, Nicole D'Aurizio, Chiara Gaudeni, Sergio Gurgone, Daniele Borzelli, Andrea D'Avella, Domenico Prattichizzo
2020 arXiv   pre-print
Towards a complete evaluation of the proposed control system, we studied the users' capability of exploiting the Implicit Kinematic Kernel both in virtual and real environments, asking subjects to track  ...  different reference signals and to control a robotic extra-finger to accomplish pick-and-place tasks.  ...  A paired-samples t-test was used to determine whether there was a statistically significant mean difference between the radii RMS error obtained when participants exploited the system to accomplish a single  ... 
arXiv:2012.03600v1 fatcat:46ltpbuw7zhixmncool4z52fxi

Implementing Multilayer Neural Network Behavior Using Polychronous Wavefront Computation

Fred Highland, Corey Hart
2016 Procedia Computer Science  
While it's has been shown to exhibit some basic computational capabilities, its use in complex neuro-computational models remains to be explored.  ...  The paper presents a model and approach for configuring PWC transponders to implement multilayer neural network behavior to provide a basis for more complex applications of the technology.  ...  A more general approach to learning useful outputs may be to apply a Spike Timing Dependent Plasticity (STDP) approach to find output nodes locations 9 .  ... 
doi:10.1016/j.procs.2016.09.307 fatcat:trn3jvb7urf7tdrkpnvns36kra

Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

Pavlyuk
2020 Algorithms  
Transfer learning is a modern concept that focuses on the application of ideas, models, and algorithms, developed in one applied area, for solving a similar problem in another area.  ...  The idea of transferring video prediction models to the urban traffic forecasting domain is validated using a large real-world traffic data set.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.  ... 
doi:10.3390/a13020039 fatcat:ofmz444gq5hhll7zn7bkm4jcoq

Label Alteration to Improve Underwater Mine Classification

David P. Williams
2011 IEEE Geoscience and Remote Sensing Letters  
To determine an appropriate number of sampling rounds, M , to consider, we exploit the work developed for multiple imputation [5] , which replaces each missing feature value with a set of M samples.  ...  All of the alarms were then manually ground-truthed visually by inspection (while also exploiting the target-deployment location information).  ... 
doi:10.1109/lgrs.2010.2088106 fatcat:w4fzo7ofxfeshnd7ohwkiu55me

Silicon strip detectors for the LHCb experiment

Olaf Steinkamp
2005 Nuclear Instruments and Methods in Physics Research Section A : Accelerators, Spectrometers, Detectors and Associated Equipment  
Silicon microstrip detectors are employed in a significant fraction of the tracking system.  ...  The Vertex Locator consists of 21 detector stations that operate inside the LHC beam pipe and are separated from the beam vacuum by a thin aluminium foil.  ...  An R-φ geometry with readout strip pitches ranging from 40 µm at small radii to 100 µm on the outside of the sensors is chosen.  ... 
doi:10.1016/j.nima.2005.01.042 fatcat:37cpqwoc7ffsti26xp3fc5eqaq

Learning efficient visual search for stimuli containing diagnostic spatial configurations and color-shape conjunctions

Eric A. Reavis, Sebastian M. Frank, Peter U. Tse
2018 Attention, Perception & Psychophysics  
Several recent imaging studies have identified neural correlates of this learning, but it remains unclear what stimulus properties participants learn to use to search efficiently.  ...  Overall, the findings suggest conjunction learning involving such stimuli might be an emergent phenomenon that reflects multiple different learning processes, each of which capitalizes on different types  ...  The research was supported by internal Dartmouth funding, Templeton Foundation Grant 14316 to P.T. and National Science Foundation Grant 1632738 to P.T.  ... 
doi:10.3758/s13414-018-1516-9 pmid:29651754 fatcat:3au36yvbcfepdglqigp7pn3bta

Emergence of social inequality in the spatial harvesting of renewable public goods

Jaideep Joshi, Åke Brännström, Ulf Dieckmann, Stefano Allesina
2020 PLoS Computational Biology  
large-scale overexploitation. (4) If costs of dispersal are significant, increased harvesting efficiency also leads to social inequality between frugal sedentary consumers and overexploitative mobile  ...  of spatial and ecological dimensions introduces new features absent in non-spatial ecological contexts, such as consumer mobility, local information availability, and strategy evolution through social learning  ...  Resource dynamics The resource density R at each location (x,y) grows logistically, with the harvesting-rate density H depending on all consumers exploiting that location, dRðx; yÞ=dt ¼ rRðx; yÞð1 À Rðx  ... 
doi:10.1371/journal.pcbi.1007483 pmid:31914166 fatcat:xnhtrgsezbhprdyngnsykjcweu

Detection of Exoplanets using Machine Learning

Amritanshu Kumar Singh, Vedant Arvind Kumbhare
2022 International Journal of Research Publication and Reviews  
Three methods for using machine learning to decide if a star has an exoplanet from transit survey data are discussed in this paper and are also used to determine which approach performs better on a labeled  ...  SMOTE (Synthetic Minority Oversampling Technique) was used to over-sample the exoplanet class to further boost the performance.  ...  Feature extraction relates to the removal in dimensionality. Conclusion CNN and SVM were used to locate transitioning exoplanets.  ... 
doi:10.55248/gengpi.2022.3.2.12 fatcat:hyhsikuslzcdnl24ek2vykf6ue

Explaining Aggregates for Exploratory Analytics

Fotis Savva, Christos Anagnostopoulos, Peter Triantafillou
2018 2018 IEEE International Conference on Big Data (Big Data)  
Explanations assume the form of a set of parametric piecewise-linear functions acquired through a statistical learning model.  ...  In XAXA, explanations for future AQs can be computed without any database (DB) access and can be used to further explore the queried data subspaces, without issuing any more queries to the DB.  ...  Therefore, (i) the analyst issues an AQ q = [x, θ]; (ii) the DBMS answers with result y ; (iii) our framework exploits pairs (q, y) to train its new statistical learning model.  ... 
doi:10.1109/bigdata.2018.8621953 dblp:conf/bigdataconf/SavvaAT18 fatcat:u4zetu327nasnlmdxsr2b5ncni

Cross-Articulation Learning for Robust Detection of Pedestrians [chapter]

Edgar Seemann, Bernt Schiele
2006 Lecture Notes in Computer Science  
On the other hand, the method generalizes well and requires relatively few training samples by crossarticulation learning.  ...  Due to the large appearance changes and intra-class variability of these objects, it is hard to define a model, which is both general and discriminative enough to capture the properties of the category  ...  In conclusion, the proposed cross-articulation learning is, while separating the influences of different articulations, able to exploit the information present in the training data to a large extent.  ... 
doi:10.1007/11861898_25 fatcat:ov4ay7b4wrcxljg4tcwuek4cre
« Previous Showing results 1 — 15 out of 8,213 results