[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… - ar** very fast. The
generative adversarial network (GAN) emerges as a promising framework, which uses …

Max-margin deep generative models for (semi-) supervised learning

C Li, J Zhu, B Zhang - IEEE transactions on pattern analysis …, 2017 - ieeexplore.ieee.org
Deep generative models (DGMs) can effectively capture the underlying distributions of
complex data by learning multilayered representations and performing inference. However …

ZhuSuan: A library for Bayesian deep learning

J Shi, J Chen, J Zhu, S Sun, Y Luo, Y Gu… - arxiv preprint arxiv …, 2017 - arxiv.org
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian
deep learning, which conjoins the complimentary advantages of Bayesian methods and …

Learning to generate with memory

C Li, J Zhu, B Zhang - International conference on machine …, 2016 - proceedings.mlr.press
Memory units have been widely used to enrich the capabilities of deep networks on
capturing long-term dependencies in reasoning and prediction tasks, but little investigation …