GAN 已被定义为*,这是 ML* ( [https://www.quora.com/What-are-some-recent-and-potentially-upcoming- 深度学习之父之一 Yann LeCun 的“深度学习突破](https://www.quora.com/What-are-some-recent-and-potentially-upcoming-breakthroughs-in-deep-learning)”)。 GAN 能够学习如何再现看起来真实的合成数据。 例如,计算机可以学习如何绘制和创建逼真的图像。 这个想法最初是由与蒙特利尔大学 Google Brain 合作的 Ian Goodfellow 提出的,最近由 OpenAI( [https://openai.com/](https://openai.com/) )提出。
GAN 已被深度学习之父之一 Yann LeCun 定义为[“这是深度学习的突破”](https://www.quora.com/What-are-some-recent-and-potentially-upcoming-breakthroughs-in-deep-learning)。 GAN 能够学习如何再现看起来真实的合成数据。 例如,计算机可以学习如何绘制和创建逼真的图像。 这个想法最初是由与蒙特利尔大学 Google Brain 合作的 Ian Goodfellow 提出的,最近由 [OpenAI](https://openai.com/)提出。
# 那么,GAN 是什么?
# 那么,GAN 是什么?
...
@@ -34,7 +34,7 @@ An example of convergence for Generator and Discriminator
...
@@ -34,7 +34,7 @@ An example of convergence for Generator and Discriminator
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.
...
@@ -543,7 +543,7 @@ In recent years, supervised learning with convolutional networks (CNNs) has seen
...
@@ -543,7 +543,7 @@ In recent years, supervised learning with convolutional networks (CNNs) has seen
●Google 的 AI 向导在神经网络上带来了新的变化: [https://www.wired.com/story/googles-ai-wizard-unveils-a-new-twist-on-neural-networks/](https://www.wired.com/story/googles-ai-wizard-unveils-a-new-twist-on-neural-networks/)
[Google 的 AI 向导在神经网络上带来了新的变化](https://www.wired.com/story/googles-ai-wizard-unveils-a-new-twist-on-neural-networks/)