4 Hits in 3.3 sec

"Dependency Bottleneck" in Auto-encoding Architectures: an Empirical Study [article]

Denny Wu, Yixiu Zhao, Yao-Hung Hubert Tsai, Makoto Yamada, Ruslan Salakhutdinov
2018 arXiv   pre-print
In the experiment, we empirically evaluate the generalization property using HSIC in both the reconstruction and prediction auto-encoding (AE) architectures.  ...  Recent works investigated the generalization properties in deep neural networks (DNNs) by studying the Information Bottleneck in DNNs.  ...  In the experiment, we empirically evaluate the generalization property of the learned latent representations in reconstruction and prediction auto-encoding (AE) architectures.  ... 
arXiv:1802.05408v1 fatcat:sltamp7gdba3ngmvu2n5bvpxzm

HSIC Bottleneck based Distributed Deep Learning Model for Load Forecasting in Smart Grid with A Comprehensive Survey

Md. Akhtaruzzaman, Mohammad Kamrul Hasan, S. Rayhan Kabir, Siti Norul Huda Sheikh Abdullah, Muhammad Jafar Sadeq, Eklas Hossain
2020 IEEE Access  
, and Auto-encoder (AE) [98] .  ...  HSIC Bottleneck has been developed based on Hilbert-Schmidt Independence Criterion (HSIC) [29] , Information Bottleneck [30] , and Dependency Bottleneck [31] theorems.  ... 
doi:10.1109/access.2020.3040083 fatcat:tsqokovkm5gpfdsnm7bph73piu

Adaptation Algorithms for Speech Recognition: An Overview

Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski
2020 IEEE Open Journal of Signal Processing  
We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.  ...  [218] used accent-dependent bottleneck features in place of i-vectors; and Turan et al. [219] used x-vector accent embeddings in a semi-supervised setting.  ...  The AED architecture ( Fig. 1(c) ) enriches the encoder-decoder model with an additional attention network which interfaces the acoustic encoder with the decoder.  ... 
doi:10.1109/ojsp.2020.3045349 fatcat:tdprznnisvc2xampkzbavjpamu

Errors and Faults [chapter]

Ana Gainaru, Franck Cappello
2015 Computer Communications and Networks  
This chapter focuses on offering an overview of failures observed in real large-scale systems and their characteristics, with an emphasis on modeling, detection, and prediction.  ...  Understanding the behavior of failures in large-scale systems is important in order to design techniques to tolerate them.  ...  Firstly, it can highlight dependability bottlenecks and might serve as a guideline for designing more reliable systems in the future.  ... 
doi:10.1007/978-3-319-20943-2_2 fatcat:44yvw6pozjbxlmhbz7kafvcapq