Filters








3,523 Hits in 3.9 sec

Selecting the Best in GANs Family: a Post Selection Inference Framework [article]

Yao-Hung Hubert Tsai, Makoto Yamada, Denny Wu, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
2018 arXiv   pre-print
We then propose a GANs analysis framework to select and test the "best" member in GANs family using the Post Selection Inference (PSI) with MMD_inc.  ...  In the experiments, we adopt the proposed framework on 7 GANs variants and compare their MMD_inc scores.  ...  We employ the Post Selection Inference (PSI) framework to test the hypothesis.  ... 
arXiv:1802.05411v2 fatcat:ma5mlaah25hytne5fagzmdrcdy

Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator [article]

Makoto Yamada, Denny Wu, Yao-Hung Hubert Tsai, Ichiro Takeuchi, Ruslan Salakhutdinov, Kenji Fukumizu
2018 arXiv   pre-print
Last, we propose a sample selection framework for analyzing different members in the Generative Adversarial Networks (GANs) family.  ...  In the paper, we propose a post selection inference (PSI) framework for divergence measure, which can select a set of statistically significant features that discriminate two distributions.  ...  MY was supported by the JST PRESTO program JPMJPR165A and partly supported by MEXT KAKENHI 16K16114.  ... 
arXiv:1802.06226v1 fatcat:kj7sqpvqkreexo7unkkkttclaa

Landscape of gene transposition-duplication within the Brassicaceae family [article]

Dong-Ha Oh, Maheshi Dassanayake
2017 bioRxiv   pre-print
The majority of tr-d events resulted in truncated open reading frames (ORFs) in the duplicated loci.  ...  Using a search based on network topology, out of a total of 17,432 OrthNets in six Brassicaceae genomes, we identified 1,394 that included gene transposition-duplication ( tr-d ) events in one or more  ...  A comparative genomics framework including the two extremophyte/halophyte crucifers, S. parvula and E. salsugineum.Boxes and stars indicate the six Brassicaceae species selected for this work and halophytes  ... 
doi:10.1101/236299 fatcat:fgftde5wrbdhzeb2e7manxwno4

Automatic Face Understanding: Recognizing Families in Photos [article]

Joseph P Robinson
2021 arXiv   pre-print
Furthermore, our model is robust with a reduced size: 1/8 the number of channels is comparable to SOTA in real-time on a CPU.  ...  We have several benchmarks in kinship verification, family classification, tri-subject verification, and large-scale search and retrieval.  ...  Thus, this is just a sliver of the larger problem of bias in ML. We show a bias for subgroups in FR caused by the selection of a single threshold.  ... 
arXiv:2102.08941v1 fatcat:eqje3jh23nb6do7crz7rw6342a

Kinship Support in Jamaican Families in the USA and Jamaica

Ivy Forsythe-Brown, Robert Joseph Taylor, Linda M. Chatters, Ishtar O. Govia, Niki Matusko, James S. Jackson
2017 Journal of African American Studies  
The NSAL sample has a national multi-stage probability design. The interviews  ...  The National Survey of American Life: Coping with Stress in the 21st Century (NSAL) is used for the analysis of Jamaican immigrants in the United States.  ...  The family solidarity model is a useful framework for understanding culturally defined patterns of kin relations and support among immigrant families.  ... 
doi:10.1007/s12111-017-9355-7 pmid:29038650 pmcid:PMC5639907 fatcat:cdlir7vqcrf3fmwtao43tsd6ei

Lawyers and Children: Wisdom and Legitimacy in Family Policy

Carl E. Schneider, Robert H. Mnookin, Robert A. Burt, David L. Chambers, Michael S. Wald, Stephen D. Sugarman, Franklin E. Zimring, Rayman L. Solomon
1986 Michigan law review  
But even an incrementalist approach ought to be informed by the best available evidence and the most appropriate analytic framework.  ...  Louise Gans, a lawyer on the staff of Community Action for Legal Services, intervened on behalf of the class of natural parents with children in foster care; Helen Buttenwieser, a lawyer whose clients  ... 
doi:10.2307/1288861 fatcat:7xoniddmdngttl63vf63dwblke

Vertebral number is highly evolvable in salamanders and newts (family Salamandridae) and variably associated with climatic parameters

Jan W. Arntzen, Wouter Beukema, Frietson Galis, Ana Ivanović, M. Brazeau
2015 Contributions to zoology  
We analysed vertebral numbers in the family Salamandridae in a phylogenetic context and calculated the relationship between vertebral changes and changes in climate and other environmental parameters.  ...  A - male biased - sexual dimorphism was only observed in Lissotriton vulgaris vulgaris in the number of trunk vertebrae and in Ommatotriton ophryticus and Lissotriton species for the number of caudal vertebrae  ...  Joger (Staatlichen Naturhistorischen Museums, Braunschweig) for the loan of specimens under their care.  ... 
doi:10.1163/18759866-08402001 fatcat:j7z7o4tijngitbubjtgfcbo4gy

DeepNeuro: an open-source deep learning toolbox for neuroimaging [article]

Andrew Beers, James Brown, Ken Chang, Katharina Hoebel, Elizabeth Gerstner, Bruce Rosen, Jayashree Kalpathy-Cramer
2018 arXiv   pre-print
In this paper, we present DeepNeuro, a deep learning framework that is best-suited to putting deep learning algorithms for neuroimaging in practical usage with a minimum of friction.  ...  We show how this framework can be used to both design and train neural network architectures, as well as modify state-of-the-art architectures in a flexible and intuitive way.  ...  Acknowledgements The Center for Clinical Data Science at Massachusetts General Hospital and the Brigham and Woman's Hospital provided technical and hardware support for the development of DeepNeuro, including  ... 
arXiv:1808.04589v1 fatcat:dxokjhvxibb6jh4sug2i7ie2em

Autonomic Workload Performance Modeling for Large-Scale Databases and Data Warehouses through Deep Belief Network with Data Augmentation using Conditional Generative Adversarial Networks

Nusrat Shaheen, Basit Raza, Ahmad Raza Shahid, Ahmad Kamran Malik
2021 IEEE Access  
A GAN based framework to solve class imbalance problem in building the classifier for credit card fraud detection is presented in study [31] .  ...  Among different features selection techniques, Random Forest feature selection remained the best in our experiments.  ...  He received his Ph.D. degree from the Vienna University of Technology (TU-Wien), Vienna, Austria. He has published a book and many research papers in reputed international journals and conferences.  ... 
doi:10.1109/access.2021.3096039 fatcat:d5ogtlrtgrg2riivmmlrcuv7z4

Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks [article]

Chin-Cheng Hsu, Hsin-Te Hwang, Yi-Chiao Wu, Yu Tsao, Hsin-Min Wang
2017 arXiv   pre-print
In this paper, we propose a non-parallel VC framework with a variational autoencoding Wasserstein generative adversarial network (VAW-GAN) that explicitly considers a VC objective when building the speech  ...  Experimental results corroborate the capability of our framework for building a VC system from unaligned data, and demonstrate improved conversion quality.  ...  In the first stage, a speakerindependent encoder E φ infers a latent content zn.  ... 
arXiv:1704.00849v3 fatcat:zqwhhbjixzb6djsk5n2ki5py7u

Sampling from Disentangled Representations of Single-Cell Data Using Generative Adversarial Networks [article]

Hengshi Yu, Joshua D Welch
2021 bioRxiv   pre-print
data in a similar way.  ...  We also develop MichiGAN, a novel neural network that combines the strengths of VAEs and GANs to sample from disentangled representations without sacrificing data generation quality.  ...  In contrast, the GAN framework consists of a two-player game between a generator network and a discriminator network [26] .  ... 
doi:10.1101/2021.01.15.426872 fatcat:kzyiuxkntbfcvfzfperxwnvkpy

FV-GAN: Finger Vein Representation Using Generative Adversarial Networks

Wenming Yang, Changqing Hui, Zhiquan Chen, Jing-Hao Xue, Qingmin Liao
2019 IEEE Transactions on Information Forensics and Security  
To address these issues, in this paper we propose a novel approach termed FV-GAN to finger vein extraction and verification, based on generative adversarial network (GAN), as the first attempt in this  ...  The experimental results on two public databases show a significant improvement by FV-GAN in finger vein verification in terms of both verification accuracy and equal error rate.  ...  ACKNOWLEDGMENT We are grateful to the Associate Editor and three anonymous reviewers for their constructive comments which largely improve our manuscript, in particular about the methodology presentation  ... 
doi:10.1109/tifs.2019.2902819 fatcat:m7md3pvl2nc4tnt2d75mvr56xy

Marital power, marital adjustment, and therapy outcome

Bernadette Gray-Little, Donald H. Baucom, Sherry L. Hamby
1996 Journal of family psychology  
A framework for conceptualizing marital conflict. In L. A. Hamerlynck, L.C. Hardy, & E.J. Marsh (Eds.), Behavior change: Methodology, concepts, and practice (pp. 309-342).  ...  At the end of treatment, egalitarian couples still had the best overall adjustment of the four groups.  ... 
doi:10.1037/0893-3200.10.3.292 fatcat:jqkzuh7zunh75dcjfz53d4c6se

PandoraGAN: Generating antiviral peptides using Generative Adversarial Network [article]

Shraddha Surana, Pooja Arora, Divye Singh, Deepti Sahasrabuddhe, Jayaraman Valadi
2021 bioRxiv   pre-print
With limited information regarding these peptides and their activity, modifying the existing peptide backbone or developing a novel peptide is very time consuming and a tedious process.  ...  To our knowledge this is the first ever use of GAN models for antiviral peptides across the viral spectrum.ResultsIn this study, we develop PandoraGAN that utilizes GAN to design bio active antiviral peptides  ...  Acknowledgements SS lead the development of the GAN architecture along with Divye S. PA conceptualised the problem and analysed the data.  ... 
doi:10.1101/2021.02.15.431193 fatcat:w4edhtcs4vhy5kefg3zs4s6uge

Generative Models for Effective ML on Private, Decentralized Datasets [article]

Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Aguera y Arcas
2020 arXiv   pre-print
We explore these methods in applications to text with differentially private federated RNNs and to images using a novel algorithm for differentially private federated GANs.  ...  Manual inspection of raw data - of representative samples, of outliers, of misclassifications - is an essential tool in a) identifying and fixing problems in the data, b) generating new modeling hypotheses  ...  AN APPLICATION TO DEBUGGING DURING INFERENCE WITH GANS We can take the GAN training framework and adapt it to FL and DP, analogous to RNN training under FL and DP in McMahan et al. (2018) via the DP-FedAvg  ... 
arXiv:1911.06679v2 fatcat:qdupc7zyh5gwpgu5yj2fim2kdu
« Previous Showing results 1 — 15 out of 3,523 results