While generative models could theoretically be implemented using a wide variety of machine learning algorithms, in practice, they are usually built with deep neural networks, which are well suited to capturing complex variations in data such as images or language.
In this book, we will focus on implementing theses deep generative models for many different applications using TensorFlow2.0. TensorFlow is a C++ framework, with APIs in the Python programming language, used to develop and productionize deep learning modles. It was open sourced by Google in 2013, and has become one of the most popular libraries for the research and deployment of neural network models.
With the 2.0 release, much of the boilerplate code that characterized development in earlier versions of the library was cleaned up with high-level abstractions, allowing us to focus on the model rather than the plumbing of the computations.
The latest version also introduced the concept of eager execution, allowing network computations to be run on demand, which will be an important benefit of implementing some of our models.
In upcoming chapters, yuuou will learn not only the underlying theory behind these models, but the practical skills needed to implement them in popular programming frameworks. In Chapter 2, Setting up a TensorFlow Lab, you will learn how to set up a cloud environment that will allow you to run TensorFlow in a distributed fashion, using the Kubeflow framework to catalog your experiments.
Indeed, as I will describe in more detail in Chapter 3, Building B locks of Deep Neural Networks, since 2006 an explosion of research into deep learning using large neural network models has produced a wide variety of generative modeling applications.
The first of these was the restricted Boltzmann machine, which is stached in multiple layers to create a deep belief network. I will describe both of these models in Chapter 4, Teaching Networks to Generate Digits. Later innovations incluided Variational Autoencoders(VAEs), which can efficiently generate complex data samples from random numbers, using techniques that I will describe in Chapter 5, Painting Pictures with Neural Networks Using VAEs.
We will also cover the algorithm used to create The Portrait of Edmond Belamy, the GAN, in more detail in Chapter6, Image Generation with GANs, of this book.
Conceptually, the GAN model creates a competition between two neural networks. One(termed the generator) produces realistic(or, in the case of the experiments by Obvious, artistic) images starting from a set of random numbers and applying a mathematical transformation. In a sense, the generator is like an art student, producing new paintings from brushstrokes and creative inspiration.
The second network, known as the discriminator, attempts to classify whether a picture comes from a set of real-world images, or whether it was created by the generator. Thus, the discriminator acts like a teacher, grading whether the student has produced work comparable to the paintings they are attempting to mimic. As the generator becomes better at fooling the discriminator, its ouput becomes closer and closer to the historical examples it is designed to copy.
There are many classes of GAN models, with additional variants covered in Chapter7, Style Transfer with GANs, and Chapter 11. Composing Music with Generative Models, in our discussion of advanced models. Another key innovation in generative models is in the domain of natural language data. By representing the complex interrelationship between words ina sentence in a computationally scalable way the Transformer network and the Bidirectional Encoder from Trasformers(BERT) model built on top of it present powerful building block to generate textual data in applications such as chatbots, which we'll cover in more detail in Chapter 9, The Rise of Methods for Text Generation, and Chapter 10, NLP2.0: Using Transformers to Generate Text
In Chapter 12, Play Video Games with Generative AI: GAIL, you will also see how models such as GANs and VAEs can be used to generate not just images or text, but sets of rules that allow game-playuing networks developed with reinforcement learning algorithms to process and navigate their enviroment more efficientlyin essence, learning to learn. Generative models are a huge field or research that is constantly growing, so unfortunately, we can't cover every topic in this book. For the interested reader, references to further topics will be provided in Chapter 13, Emerging Applications in Generative AI.
To get started with come background information, let's discuss the rule of probability.
댓글 없음:
댓글 쓰기