Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play

Přední strana obálky
"O'Reilly Media, Inc.", 28. 6. 2019 - Počet stran: 330

Generative modeling is one of the hottest topics in AI. It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models and world models.

Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you’ll understand how to make your models learn more efficiently and become more creative.

  • Discover how variational autoencoders can change facial expressions in photos
  • Build practical GAN examples from scratch, including CycleGAN for style transfer and MuseGAN for music generation
  • Create recurrent generative models for text generation and learn how to improve the models using attention
  • Understand how generative models can help agents to accomplish tasks within a reinforcement learning setting
  • Explore the architecture of the Transformer (BERT, GPT-2) and image generation models such as ProGAN and StyleGAN
 

Vybrané stránky

Obsah

Oddíl 1
Oddíl 2
Oddíl 3
Oddíl 4
Oddíl 5
Oddíl 6
Oddíl 7
Oddíl 8
Oddíl 13
Oddíl 14
Oddíl 15
Oddíl 16
Oddíl 17
Oddíl 18
Oddíl 19
Oddíl 20

Oddíl 9
Oddíl 10
Oddíl 11
Oddíl 12
Oddíl 21
Oddíl 22
Oddíl 23
Oddíl 24

Další vydání - Zobrazit všechny

Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play
David Foster
Omezený náhled - 2019
Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play
David Foster
Náhled není k dispozici. - 2019

Běžně se vyskytující výrazy a sousloví

Adversarial Networks agent attention mechanism batch normalization batch_size BigGAN book repository build cell chapter CMA-ES Compiling concatenated Conv2D convolutional layers critic CycleGAN dataset decoder deep learning deep neural network defined Dense layer dimensions discriminative modeling domain Dropout Layers encoder encoder-decoder epochs filters Granny Smith hidden input image Keras latent space log_var Long Short-Term Memory loss function LSTM layer LSTM network machine learning matrix MDN-RNN model architecture MuseGAN Naive Bayes neural style transfer normal distribution notebook observation output painting parameters pdata pixels predict problem Python random real environment recurrent layer recurrent neural network reinforcement learning relu ResNet reward sample space score sequence shown in Figure softmax strides StyleGAN supervised learning techniques tensor TensorFlow timestep tokens track training process training set U-Net update values variational autoencoder vector vector of length Wasserstein loss weights WGAN WGAN-GP word World Models Wrodl z_dim

O autorovi (2019)

David Foster is the co-founder of Applied Data Science, a data science consultancy delivering bespoke solutions for clients. He holds an MA in Mathematics from Trinity College, Cambridge, UK and an MSc in Operational Research from the University of Warwick.David has won several international machine learning competitions, including the Innocentive Predicting Product Purchase challenge and was awarded first prize for a visualisation that enables a pharmaceutical company in the US to optimize site selection for clinical trials.He is an active participant in the online data science community and has authored several successful blog posts on deep reinforcement learning including ‘How To Build Your Own AlphaZero AI’.

Bibliografické údaje

NázevGenerative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play
AutorDavid Foster
Vydavatel"O'Reilly Media, Inc.", 2019
ISBN1492041890, 9781492041894
DélkaPočet stran: 330
  
Exportovat citaciBiBTeX EndNote RefMan