跳转到内容

用户:Llasioneisall/Sandbox

维基百科,自由的百科全书

生成对抗网络 https://en.wikipedia.org/wiki/Generative_adversarial_networks

自动编码器 https://en.wikipedia.org/wiki/Autoencoder

Generative adversarial networks (GANs) are a type of artificial intelligence algorithms used in unsupervised machine learning, implemented by a system of two neural networks competing against each other in a zero-sum game framework. They were first introduced by Ian Goodfellow et al. in 2014.[1]

This technique can generate photographs that look authentic to human observers.[2]

Method

[编辑]

One network is generative and one is discriminative.[1] Typically, the generative network is taught to map from a latent space to a particular data distribution of interest, and the discriminative network is simultaneously taught to discriminate between instances from the true data distribution and synthesized instances produced by the generator. The generative network's training objective is to increase the error rate of the discriminative network (i.e., "fool" the discriminator network by producing novel synthesized instances that appear to have come from the true data distribution). These models are used for computer vision tasks.[1][3]

In practice, a particular dataset serves as the training data for the discriminator. Training the discriminator involves presenting the discriminator with samples from the dataset and samples synthesized by the generator, and backpropagating from a binary classification loss. In order to produce a sample, typically the generator is seeded with a randomized input that is sampled from a predefined latent space (e.g., a multivariate normal distribution). Training the generator involves back-propagating the negation of the binary classification loss of the discriminator. The generator adjusts its parameters so that the training data and generated data cannot be distinguished by the discriminator model. The goal is to find a setting of parameters that makes generated data look like the training data to the discriminator network.[4] In practice, the generator is typically a deconvolutional neural network, and the discriminator is a convolutional neural network.

The idea to infer models in a competitive setting (model versus discriminator) was first proposed by Li, Gauci and Gross in 2013.[5] Their method is used for behavioral inference. It is termed Turing Learning,[6] as the setting is akin to that of a Turing test.

Application

[编辑]

GANs can be used to produce samples of photorealistic images for the purposes of visualizing new interior/industrial design, shoes, bags and clothing items or items for computer games' scenes. These networks were reported to be used by Facebook.[7] Recently, GANs have been able to model rudimentary patterns of motion in video.[8] They have also been used to reconstruct 3D models of objects from images [9] and to improve astronomical images.[10]

References

[编辑]
  1. ^ 1.0 1.1 1.2 Goodfellow, Ian J.; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua. Generative Adversarial Networks. 2014. arXiv:1406.2661可免费查阅 [stat.ML]. 
  2. ^ Salimans, Tim; Goodfellow, Ian; Zaremba, Wojciech; Cheung, Vicki; Radford, Alec; Chen, Xi. Improved Techniques for Training GANs. 2016. arXiv:1606.03498可免费查阅 [cs.LG]. 
  3. ^ Luc, Pauline; Couprie, Camille; Chintala, Soumith; Verbeek, Jakob. Semantic Segmentation using Adversarial Networks. NIPS Workshop on Adversarial Training, Dec , Barcelona, Spain. 2016-11-25, 2016. arXiv:1611.08408可免费查阅. 
  4. ^ Andrej Karpathy, Pieter Abbeel, Greg Brockman, Peter Chen, Vicki Cheung, Rocky Duan, Ian Goodfellow, Durk Kingma, Jonathan Ho, Rein Houthooft, Tim Salimans, John Schulman, Ilya Sutskever, And Wojciech Zaremba, Generative Models, OpenAI, [April 7, 2016] 
  5. ^ Li, Wei; Gauci, Melvin; Gross, Roderich. A Coevolutionary Approach to Learn Animal Behavior Through Controlled Interaction. Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation (GECCO 2013). Amsterdam, The Netherlands: ACM: 223–230. July 6, 2013. 
  6. ^ Li, Wei; Gauci, Melvin; Groß, Roderich. Turing learning: a metric-free approach to inferring behavior and its application to swarms. Swarm Intelligence. 30 August 2016, 10 (3): 211–243. doi:10.1007/s11721-016-0126-1. 
  7. ^ Greenemeier, Larry. When Will Computers Have Common Sense? Ask Facebook. Scientific American. June 20, 2016 [July 31, 2016]. 
  8. ^ http://web.mit.edu/vondrick/tinyvideo/
  9. ^ http://3dgan.csail.mit.edu/
  10. ^ Schawinski, Kevin; Zhang, Ce; Zhang, Hantian; Fowler, Lucas; Santhanam, Gokula Krishnan. Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit. 2017-02-01. arXiv:1702.00403可免费查阅 [astro-ph.IM]. 
[编辑]


Template:Computer-science-stub Template:Computing-stub


新推荐条目RULE

[编辑]

https://wikicn.playgoteam.workers.dev/wiki/Wikipedia:%E6%96%B0%E6%9D%A1%E7%9B%AE%E6%8E%A8%E8%8D%90/%E5%80%99%E9%80%89

[沙沙沙沙沙沙] [沙沙沙沙沙沙]

Current Target: 编辑次数1000次(含)-2000次(不含),新条目推荐3条或以上,使用字母B


创新相关条目: 人工神经网络 https://wikicn.playgoteam.workers.dev/wiki/%E4%BA%BA%E5%B7%A5%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C

机器学习相关 https://wikicn.playgoteam.workers.dev/wiki/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0 https://wikicn.playgoteam.workers.dev/wiki/%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD%E7%AE%97%E6%B3%95

数学类: https://en.wikipedia.org/wiki/Inference https://en.wikipedia.org/wiki/Limit_of_a_function https://en.wikipedia.org/wiki/Rational_choice_theory https://en.wikipedia.org/wiki/Triangulation https://en.wikipedia.org/wiki/Crop_rotation

杖道 https://en.wikipedia.org/wiki/J%C5%8Dd%C5%8D https://ja.wikipedia.org/wiki/%E9%89%84%E6%8B%B33

学习式机器人 https://en.wikipedia.org/wiki/Developmental_robotics

汽油弹 http://en.wikipedia.org/wiki/Molotov_cocktail#cite_ref-online_1-0 http://blog.udn.com/aibmk/408901


改善: Segmentation https://wikicn.playgoteam.workers.dev/wiki/%E5%9B%BE%E5%83%8F%E5%88%86%E5%89%B2

Merry Christmas, Mr. Lawrence http://en.wikipedia.org/wiki/Merry_Christmas,_Mr._Lawrence https://wikicn.playgoteam.workers.dev/wiki/%E4%BF%98%E8%99%9C_(%E9%9B%BB%E5%BD%B1)


能量收成英语Energy harvesting 热传导发电器 https://en.wikipedia.org/wiki/Thermoelectric_generator

测试

Level-2 heading (A)

[编辑]

Level-3 heading (B)

[编辑]

Level-2 heading (C)

[编辑]
Level-6 heading (D)
[编辑]

Level-1 heading (E)

[编辑]

Level-2 heading (F)

[编辑]

Level-3 heading (G)

[编辑]