Filters








47,885 Hits in 3.7 sec

Robustness via Uncertainty-aware Cycle Consistency [article]

Uddeshya Upadhyay, Yanbei Chen, Zeynep Akata
2021 arXiv   pre-print
To address this, we propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution  ...  Existing methods learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen perturbations  ...  Uncertainty-aware Generalized Adaptive Cycle-consistency (UGAC) We present the formulation of the unpaired image-to-image translation problem.  ... 
arXiv:2110.12467v1 fatcat:owggkflpu5c25mxqy4qxhlqwyu

Table of contents

2021 IEEE Transactions on Neural Networks and Learning Systems  
Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling ....................... .............................................................................. H.  ...  Maybank Inductive Structure Consistent Hashing via Flexible Semantic Calibration ................................................... ...................................................... Z.  ... 
doi:10.1109/tnnls.2021.3112415 fatcat:76cvoarxv5gfxca5ziikpsss5m

Scalable Robust Kidney Exchange

Duncan C McElfresh, Hoda Bidkhori, John P Dickerson
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Transactions in barter exchanges are often facilitated via a central clearinghouse that must match participants even in the face of uncertainty—over participants, existence and quality of potential trades  ...  For each type of uncertainty we demonstrate the benefits of robustness on real data from a large, fielded kidney exchange in the United States.  ...  A maximumcardinality matching algorithm would select the 5-chain, denoted with dashed edges; however, the smaller matching consisting of two disjoint 2-cycles, shown with solid edges, may be more robust  ... 
doi:10.1609/aaai.v33i01.33011077 fatcat:b6rtna7pf5b6lgpn7lvkdtde2q

Robust Neural Regression via Uncertainty Learning [article]

Akib Mashrur and Wei Luo and Nayyar A. Zaidi and Antonio Robles-Kelly
2021 arXiv   pre-print
Compared with more complex models such as MC-Dropout or SDE-Net, our proposed network is simpler to implement and more robust (insensitive to varying aleatoric and epistemic uncertainty).  ...  The two sub-networks have shared representations and are trained via two complementary loss functions for the prediction and the uncertainty estimates, with interleaving steps as in a cooperative game.  ...  Uncertainty quantification via neural networks is an active field of research.  ... 
arXiv:2110.06395v1 fatcat:kfnictqzwzejtputu7qoacuhqq

Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement [article]

Uddeshya Upadhyay, Viswanath P. Sudarshan, Suyash P. Awate
2021 arXiv   pre-print
However, these methods do not focus on (i)~robustness of the models to out-of-distribution (OOD)-noisy data and (ii)~uncertainty quantification.  ...  This demands robust methods that can quantify uncertainty in the prediction for making informed decisions, especially for critical areas such as medical imaging.  ...  Additionally, some methods also impose a cycle-consistency penalty to constraint the ill-posed translation problem [45, 21, 12] .  ... 
arXiv:2110.03343v1 fatcat:3szhroycjfhijmnz2w5nfo7wny

Economic Policy Uncertainty Spillovers in Booms and Busts

Giovanni Caggiano, Efrem Castelnuovo, Juan Manuel Figueres
2019 Oxford Bulletin of Economics and Statistics  
Unemployment in Canada is shown to react to uncertainty shocks in economic busts only.  ...  According to this channel, jumps in US uncertainty foster economic policy uncertainty in Canada in the ...rst place and, because of the latter, lead to a temporary increase in the Canadian unemployment  ...  However, labor market 12 We are aware of two o¢ cial datings of the business cycle for Canada.  ... 
doi:10.1111/obes.12323 fatcat:cacemagkozfczkwxu7gxu7p3wm

Economic Policy Uncertainty Spillovers in Booms and Busts

Giovanni Caggiano, Efrem Castelnuovo, Juan Manuel Figueres
2017 Social Science Research Network  
Unemployment in Canada is shown to react to uncertainty shocks in economic busts only.  ...  According to this channel, jumps in US uncertainty foster economic policy uncertainty in Canada in the first place and, because of the latter, lead to a temporary increase in the Canadian unemployment  ...  However, labor market 12 We are aware of two o¢ cial datings of the business cycle for Canada.  ... 
doi:10.2139/ssrn.2972967 fatcat:qsnu4nxdqvfvbbxnnxnvfalldu

Scalable Robust Kidney Exchange [article]

Duncan C McElfresh, Hoda Bidkhori, John P Dickerson
2018 arXiv   pre-print
Transactions in barter exchanges are often facilitated via a central clearinghouse that must match participants even in the face of uncertainty---over participants, existence and quality of potential trades  ...  For each type of uncertainty we demonstrate the benefits of robustness on real data from a large, fielded kidney exchange in the United States.  ...  A maximumcardinality matching algorithm would select the 5-chain, denoted with dashed edges; however, the smaller matching consisting of two disjoint 2-cycles, shown with solid edges, may be more robust  ... 
arXiv:1811.03532v1 fatcat:vbkkhdadfjfzhczp42hm24xq3i

Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration [article]

Christian Tomani, Florian Buettner
2021 arXiv   pre-print
That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift.  ...  Recent efforts to account for predictive uncertainty include post-processing steps for trained neural networks, Bayesian neural networks as well as alternative non-Bayesian approaches such as ensemble  ...  FALCON results in consistently well calibrated and robust predictions across all perturbation strategies.  ... 
arXiv:2012.10923v2 fatcat:gsjqr5exqbffvigwy7jzowlwcm

SMErobotics: Smart Robots for Flexible Manufacturing

Alexander Perzylo, Markus Rickert, Bjoern Kahl, Nikhil Somani, Christian Lehmann, Alexander Kuss, Stefan Profanter, Anders Billeso Beck, Mathias Haage, Mikkel Rath Hansen, Malene Tofveson Nibe, Maximo A. Roa (+7 others)
2019 IEEE robotics & automation magazine  
We implemented uncertainty-aware skills for snap-fitting parts and inserting screws (see the "Uncertainty-Aware Skills" section).  ...  The developed methods for uncertainty-aware robust automation not only enable the robot to perform more challenging tasks; they also increase the level of abstraction of decision making, further improving  ... 
doi:10.1109/mra.2018.2879747 fatcat:s4nidua77ndj3m36exwxliomdu

Optimal Experimental Design for Gene Regulatory Networks in the Presence of Uncertainty

Roozbeh Dehghannasiri, Byung-Jun Yoon, Edward R. Dougherty
2015 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
We demonstrate the effectiveness of the proposed method via extensive simulations based on synthetic and real regulatory networks.  ...  Index Terms Mean objective cost of uncertainty (MOCU), experimental design, gene regulatory network (GRN), network intervention. !  ...  The results based on the mammalian cell cycle network are consistent with the results obtained from the synthetic networks.  ... 
doi:10.1109/tcbb.2014.2377733 pmid:26357334 fatcat:xxzdfqwz2rgubefpppdwddnbvi

Normalisation and weighting in life cycle assessment: quo vadis?

Massimo Pizzol, Alexis Laurent, Serenella Sala, Bo Weidema, Francesca Verones, Christoph Koffler
2016 The International Journal of Life Cycle Assessment  
robustness.  ...  , uncertainty and complexity.  ...  "Normalisation and Weighting in Life Cycle Assessment: Quo Vadis?" The International Journal of Life Cycle Assessment. DOI: 10.1007/s11367-016-1199-1  ... 
doi:10.1007/s11367-016-1199-1 fatcat:u2oyqvkrgvglpj46sxczzmd27y

Robustness Issues of Timing and Synchronization for Free Electron Lasers [article]

Zheqiao Geng
2019 arXiv   pre-print
This article focuses on the robustness of the timing and synchronization systems, such as the time uncertainty of the RF pulse related with the trigger, the phase uncertainty of frequency dividers after  ...  This is guaranteed by the timing and synchronization systems that should be robust under the situations like a power cycle in the master oscillator, timing master, reference frequency distribution devices  ...  The robustness of the time relations should be emphasized if one expect the beam to be restored quickly after a power cycle of the timing, synchronization and LLRF devices.  ... 
arXiv:1910.04677v1 fatcat:wkg5xluxrzcsnfzoygj2ds7pya

The ECORA framework: A hybrid architecture for context-oriented pervasive computing

Amir Padovitz, Seng W. Loke, Arkady Zaslavsky
2008 Pervasive and Mobile Computing  
The use of a centralized reasoning engine provides powerful reasoning capabilities and deploying context-aware mobile agents enables agility and robustness of components in the pervasive system.  ...  This paper presents the ECORA framework for context-aware computing, which is designed with a focus on reasoning about context under uncertainty and addressing issues of heterogeneity, scalability, communication  ...  In Section 5, we present case studies demonstrating different aspects of the framework, including rapid prototyping of context-aware applications, reasoning about situations via the framework, under uncertainty  ... 
doi:10.1016/j.pmcj.2007.10.002 fatcat:owc6vhfymjed7ke3pcxuztq3ji

Google It Up! A Google Trends-Based Uncertainty Index for the United States and Australia

Efrem Castelnuovo, Trung Duc Tran
2017 Social Science Research Network  
VARs are estimated via OLS.  ...  Robustness checks.  ... 
doi:10.2139/ssrn.3050294 fatcat:szpiqxgvwreu3isvdk3jiyv4ui
« Previous Showing results 1 — 15 out of 47,885 results