在最早的对抗式生成网络的论文中,生成器和分类器用的都是全联接层,所以没有办法很好的生成图片数据,也没有办法做的很深。所以在随后的论文中,人们提出了深度卷积对抗式生成网络(deep convolutional generative adversarial network or DCGAN)\[[2](#参考文献)\]。在DCGAN中,生成器 G 是由多个卷积转置层(transposed convolution)组成的,这样可以用更少的参数来生成质量更高的图片。具体网络结果可参见图3。
1. Bengio Y, Ducharme R, Vincent P, et al. [A neural probabilistic language model](http://www.jmlr.org/papers/volume3/bengio03a/bengio03a.pdf)[J]. journal of machine learning research, 2003, 3(Feb): 1137-1155.
1. Goodfellow I, Pouget-Abadie J, Mirza M, et al. [Generative adversarial nets](https://arxiv.org/pdf/1406.2661v1.pdf)[C] Advances in Neural Information Processing Systems. 2014
2. Mikolov T, Sutskever I, Chen K, et al. [Distributed representations of words and phrases and their compositionality](http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf)[C]//Advances in neural information processing systems. 2013: 3111-3119.
2. Radford A, Metz L, Chintala S. [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/pdf/1511.06434v2.pdf)[C] arXiv preprint arXiv:1511.06434. 2015
3. Mikolov T, Kombrink S, Deoras A, et al. [Rnnlm-recurrent neural network language modeling toolkit](http://www.fit.vutbr.cz/~imikolov/rnnlm/rnnlm-demo.pdf)[C]//Proc. of the 2011 ASRU Workshop. 2011: 196-201.
3. Kingma D.P. and Welling M. [Auto-encoding variational bayes](https://arxiv.org/pdf/1312.6114v10.pdf)[C] arXiv preprint arXiv:1312.6114. 2013
4. Mikolov T, Chen K, Corrado G, et al. [Efficient estimation of word representations in vector space\[J\]](https://arxiv.org/pdf/1301.3781.pdf). arXiv preprint arXiv:1301.3781, 2013.
\ No newline at end of file
<!-- 5. Mikolov T, Karafiát M, Burget L, et al. [Recurrent neural network based language model](http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf)[C]//Interspeech. 2010, 2: 3. -->