[HTML][HTML] A state-of-the-art survey on deep learning theory and architectures

MZ Alom, TM Taha, C Yakopcic, S Westberg, P Sidike… - electronics, 2019 - mdpi.com
In recent years, deep learning has garnered tremendous success in a variety of application
domains. This new field of machine learning has been growing rapidly and has been …

The history began from alexnet: A comprehensive survey on deep learning approaches

MZ Alom, TM Taha, C Yakopcic, S Westberg… - arxiv preprint arxiv …, 2018 - arxiv.org
Deep learning has demonstrated tremendous success in variety of application domains in
the past few years. This new field of machine learning has been growing rapidly and applied …

Lamda: Language models for dialog applications

R Thoppilan, D De Freitas, J Hall, N Shazeer… - arxiv preprint arxiv …, 2022 - arxiv.org
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of
Transformer-based neural language models specialized for dialog, which have up to 137B …

Learning from noisy labels with distillation

Y Li, J Yang, Y Song, L Cao… - Proceedings of the …, 2017 - openaccess.thecvf.com
The ability of learning from noisy labels is very useful in many visual recognition tasks, as a
vast amount of data with noisy labels are relatively easy to obtain. Traditionally, label noise …

[HTML][HTML] Augmenting organizational decision-making with deep learning algorithms: Principles, promises, and challenges

YR Shrestha, V Krishna, G von Krogh - Journal of Business Research, 2021 - Elsevier
The current expansion of theory and research on artificial intelligence in management and
organization studies has revitalized the theory and research on decision-making in …

Regularizing deep neural networks by noise: Its interpretation and optimization

H Noh, T You, J Mun, B Han - Advances in neural …, 2017 - proceedings.neurips.cc
Overfitting is one of the most critical challenges in deep neural networks, and there are
various types of regularization methods to improve generalization performance. Injecting …

In defense of the triplet loss again: Learning robust person re-identification with fast approximated triplet loss and label distillation

Y Yuan, W Chen, Y Yang… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
The comparative losses (typically, triplet loss) are appealing choices for learning person re-
identification (ReID) features. However, the triplet loss is computationally much more …

Autogan-distiller: Searching to compress generative adversarial networks

Y Fu, W Chen, H Wang, H Li, Y Lin, Z Wang - arxiv preprint arxiv …, 2020 - arxiv.org
The compression of Generative Adversarial Networks (GANs) has lately drawn attention,
due to the increasing demand for deploying GANs into mobile devices for numerous …

Gan slimming: All-in-one gan compression by a unified optimization framework

H Wang, S Gui, H Yang, J Liu, Z Wang - European Conference on …, 2020 - Springer
Generative adversarial networks (GANs) have gained increasing popularity in various
computer vision applications, and recently start to be deployed to resource-constrained …

Advanced dropout: A model-free methodology for bayesian dropout optimization

J **e, Z Ma, J Lei, G Zhang, JH Xue… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural
networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate …