2024-02-08 19:10:19

totrans/gen-dl_12.yaml

@@ -1,51 +1,68 @@
 - en: Part III. Applications
+  id: totrans-0
   prefs:
   - PREF_H1
   type: TYPE_NORMAL
+  zh: 第三部分. 应用
 - en: In [Part III](#part_applications), we will explore some of the key applications
     of the generative modeling techniques that we have seen so far, across images,
     text, music, and games. We will also see how these domains can be traversed using
     state-of-the-art multimodal models.
+  id: totrans-1
   prefs: []
   type: TYPE_NORMAL
+  zh: 在第三部分中，我们将探索迄今为止所见的生成建模技术在图像、文本、音乐和游戏等领域的一些关键应用。我们还将看到如何使用最先进的多模态模型穿越这些领域。
 - en: In [Chapter 9](ch09.xhtml#chapter_transformer) we shall turn our attention to
     Transformers, a start-of-the-art architecture that powers most modern-day text
     generation models. In particular, we shall explore the inner workings of GPT and
     build our own version using Keras, and we’ll see how it forms the foundation of
     tools such as ChatGPT.
+  id: totrans-2
   prefs: []
   type: TYPE_NORMAL
+  zh: 在第9章中，我们将把注意力转向Transformers，这是一种现代文本生成模型的先进架构。特别是，我们将探索GPT的内部工作原理，并使用Keras构建我们自己的版本，我们将看到它如何构建了诸如ChatGPT之类的工具的基础。
 - en: In [Chapter 10](ch10.xhtml#chapter_image_generation) we will look at some of
     the most important GAN architectures that have influenced image generation, including
     ProGAN, StyleGAN, StyleGAN2, SAGAN, BigGAN, VQ-GAN, and ViT VQ-GAN. We shall explore
     the key contributions of each and look to understand how the technique has evolved
     over time.
+  id: totrans-3
   prefs: []
   type: TYPE_NORMAL
+  zh: 在第10章中，我们将看一些对图像生成产生影响的最重要的GAN架构，包括ProGAN、StyleGAN、StyleGAN2、SAGAN、BigGAN、VQ-GAN和ViT
+    VQ-GAN。我们将探索每个架构的关键贡献，并了解这种技术如何随着时间的推移而发展。
 - en: '[Chapter 11](ch11.xhtml#chapter_music) looks at music generation, which presents
     additional challenges such as modeling musical pitch and rhythm. We’ll see that
     many of the techniques that work for text generation (such as Transformers) can
     also be applied in this domain, but we’ll also explore a deep learning architecture
     known as MuseGAN that applies a GAN-based approach to generating music.'
+  id: totrans-4
   prefs: []
   type: TYPE_NORMAL
+  zh: 第11章探讨音乐生成，这带来了额外的挑战，比如对音乐音高和节奏进行建模。我们将看到许多适用于文本生成的技术（如Transformers）也可以应用于这个领域，但我们还将探索一种称为MuseGAN的深度学习架构，该架构应用了基于GAN的方法来生成音乐。
 - en: '[Chapter 12](ch12.xhtml#chapter_world_models) shows how generative models can
     be used within other machine learning domains, such as reinforcement learning.
     We will focus on the “World Models” paper, which shows how a generative model
     can be used as the environment in which the agent trains, allowing it to train
     within a hallucinated dream version of the environment rather than the real thing.'
+  id: totrans-5
   prefs: []
   type: TYPE_NORMAL
+  zh: 第12章展示了生成模型如何在其他机器学习领域中使用，比如强化学习。我们将重点关注“世界模型”论文，该论文展示了如何将生成模型用作代理训练的环境，使其能够在幻想的梦境版本的环境中进行训练，而不是真实环境。
 - en: In [Chapter 13](ch13.xhtml#chapter_multimodal) we will explore state-of-the-art
     multimodal models that cross over domains such as images and text. This includes
     text-to-image models such as DALL.E 2, Imagen, and Stable Diffusion, as well as
     visual language models such as Flamingo.
+  id: totrans-6
   prefs: []
   type: TYPE_NORMAL
+  zh: 在第13章中，我们将探索跨越图像和文本等领域的最先进的多模态模型。这包括文本到图像模型，如DALL.E 2、Imagen和Stable Diffusion，以及视觉语言模型，如Flamingo。
 - en: Finally, [Chapter 14](ch14.xhtml#chapter_conclusion) summarizes the generative
     AI journey so far, the current generative AI landscape, and where we may be heading
     in the future. We will explore how generative AI may change the way we live and
     work, as well as considering whether it has the potential to unlock deeper forms
     of artificial intelligence in the years to come.
+  id: totrans-7
   prefs: []
   type: TYPE_NORMAL
+  zh: 最后，在第14章中总结了迄今为止的生成人工智能之旅，当前的生成人工智能格局，以及我们未来可能走向何方。我们将探讨生成人工智能如何改变我们的生活和工作方式，以及考虑它是否有潜力在未来几年解锁更深层次的人工智能形式。