[动手学深度学习]生成对抗网络GAN学习笔记

news2024/11/25 12:52:39

论文原文：Generative Adversarial Nets (neurips.cc)

李沐GAN论文逐段精读：GAN论文逐段精读【论文精读】_哔哩哔哩_bilibili

论文代码：http://www.github.com/goodfeli/adversarial

Ian, J. et al. (2014) 'Generative adversarial network', NIPS'14: Proceedings of the 27th International Conference on Neural Information Processing Systems, Vol. 2, pp 2672–2680. doi: https://doi.org/10.48550/arXiv.1406.2661

未完待续

1. GAN

1.1. 整体实现步骤

1.2. GAN理念

1.3. GAN弊端和局限

2. GAN论文原文学习

2.1. Abstract

①They combined generative model $G$ and discriminative model $D$ together, which forms a new model. $G$ is the "cheating" part which focus on imitating and $D$ is the "distinguishing" part which focus on distinguishing where the data comes from.

②This model is rely on a "minmax" function

③GAN does not need Markov chains or unrolled approximate inference nets

④They designed qualitative and quantitative evaluation to analyse the feasibility of GAN

2.2. Introduction

①The authors praised deep learning and briefly mentioned its prospects

②Due to the difficulty of fitting or approximating the distribution of the ground truth, the designed a new generative model

③They compare the generated model to the person who makes counterfeit money, and the discriminative model to the police. Both parties will mutually promote and grow. The authors ultimately hope that the ability of the counterfeiter can be indistinguishable from the genuine product

④Both $G$ and $D$ are MLP, and $G$ passes random noise

⑤They just adopt backpropagation and dropout in training

corpora 全集；corpus 的复数

counterfeiter n.伪造者;制假者;仿造者

2.3. Related work

2.4. Adversarial nets

2.5. Theoretical Results

2.5.1. Global Optimality of p_g = p_data

2.5.2. Convergence of Algorithm 1

2.6. Experiments

2.7. Advantages and disadvantages

2.8. Conclusions and future work