Advanced deep learning with Keras : apply deep learning techniques, autoencoders, GANs, variational autoencoders, deep reinforcement learning, policy gradients, and more / / Rowel Atienza |
Autore | Atienza Rowel |
Edizione | [1st edition] |
Pubbl/distr/stampa | London, England : , : Packt Publishing, Limited, , [2018] |
Descrizione fisica | 1 online resource (368 pages) |
Disciplina | 006.32 |
Soggetto topico |
Machine learning
Neural networks (Computer science) |
Formato | Materiale a stampa ![]() |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto |
Cover -- Copyright -- Packt upsell -- Contributors -- Table of Contents -- Preface -- Chapter 1: Introducing Advanced Deep Learning with Keras -- Why is Keras the perfect deep learning library? -- Installing Keras and TensorFlow -- Implementing the core deep learning models - MLPs, CNNs and RNNs -- The difference between MLPs, CNNs, and RNNs -- Multilayer perceptrons (MLPs) -- MNIST dataset -- MNIST digits classifier model -- Building a model using MLPs and Keras -- Regularization -- Output activation and loss function -- Optimization -- Performance evaluation -- Model summary -- Convolutional neural networks (CNNs) -- Convolution -- Pooling operations -- Performance evaluation and model summary -- Recurrent neural networks (RNNs) -- Conclusion -- Chapter 2: Deep Neural Networks -- Functional API -- Creating a two-input and one-output model -- Deep residual networks (ResNet) -- ResNet v2 -- Densely connected convolutional networks (DenseNet) -- Building a 100-layer DenseNet-BC for CIFAR10 -- Conclusion -- References -- Chapter 3: Autoencoders -- Principles of autoencoders -- Building autoencoders using Keras -- Denoising autoencoder (DAE) -- Automatic colorization autoencoder -- Conclusion -- References -- Chapter 4: Generative Adversarial Networks (GANs) -- An overview of GANs -- Principles of GANs -- GAN implementation in Keras -- Conditional GAN -- Conclusion -- References -- Chapter 5: Improved GANs -- Wasserstein GAN -- Distance functions -- Distance function in GANs -- Use of Wasserstein loss -- WGAN implementation using Keras -- Least-squares GAN (LSGAN) -- Auxiliary classifier GAN (ACGAN) -- Conclusion -- References -- Chapter 6: Disentangled Representation GANs -- Disentangled representations -- InfoGAN -- Implementation of InfoGAN in Keras -- Generator outputs of InfoGAN -- StackedGAN -- Implementation of StackedGAN in Keras.
Generator outputs of StackedGAN -- Conclusion -- Reference -- Chapter 7: Cross-Domain GANs -- Principles of CycleGAN -- The CycleGAN Model -- Implementing CycleGAN using Keras -- Generator outputs of CycleGAN -- CycleGAN on MNIST and SVHN datasets -- Conclusion -- References -- Chapter 8: Variational Autoencoders (VAEs) -- Principles of VAEs -- Variational inference -- Core equation -- Optimization -- Reparameterization trick -- Decoder testing -- VAEs in Keras -- Using CNNs for VAEs -- Conditional VAE (CVAE) -- -VAE: VAE with disentangled latent representations -- Conclusion -- References -- Chapter 9: Deep Reinforcement Learning -- Principles of reinforcement learning (RL) -- The Q value -- Q-Learning example -- Q-Learning in Python -- Nondeterministic environment -- Temporal-difference learning -- Q-Learning on OpenAI gym -- Deep Q-Network (DQN) -- DQN on Keras -- Double Q-Learning (DDQN) -- Conclusion -- References -- Chapter 10: Policy Gradient Methods -- Policy gradient theorem -- Monte Carlo policy gradient (REINFORCE) method -- REINFORCE with baseline method -- Actor-Critic method -- Advantage Actor-Critic (A2C) method -- Policy Gradient methods with Keras -- Performance evaluation of policy gradient methods -- Conclusion -- References -- Other Books You May Enjoy -- Index. |
Record Nr. | UNINA-9910795323903321 |
Atienza Rowel
![]() |
||
London, England : , : Packt Publishing, Limited, , [2018] | ||
![]() | ||
Lo trovi qui: Univ. Federico II | ||
|
Advanced deep learning with Keras : apply deep learning techniques, autoencoders, GANs, variational autoencoders, deep reinforcement learning, policy gradients, and more / / Rowel Atienza |
Autore | Atienza Rowel |
Edizione | [1st edition] |
Pubbl/distr/stampa | London, England : , : Packt Publishing, Limited, , [2018] |
Descrizione fisica | 1 online resource (368 pages) |
Disciplina | 006.32 |
Soggetto topico |
Machine learning
Neural networks (Computer science) |
Formato | Materiale a stampa ![]() |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto |
Cover -- Copyright -- Packt upsell -- Contributors -- Table of Contents -- Preface -- Chapter 1: Introducing Advanced Deep Learning with Keras -- Why is Keras the perfect deep learning library? -- Installing Keras and TensorFlow -- Implementing the core deep learning models - MLPs, CNNs and RNNs -- The difference between MLPs, CNNs, and RNNs -- Multilayer perceptrons (MLPs) -- MNIST dataset -- MNIST digits classifier model -- Building a model using MLPs and Keras -- Regularization -- Output activation and loss function -- Optimization -- Performance evaluation -- Model summary -- Convolutional neural networks (CNNs) -- Convolution -- Pooling operations -- Performance evaluation and model summary -- Recurrent neural networks (RNNs) -- Conclusion -- Chapter 2: Deep Neural Networks -- Functional API -- Creating a two-input and one-output model -- Deep residual networks (ResNet) -- ResNet v2 -- Densely connected convolutional networks (DenseNet) -- Building a 100-layer DenseNet-BC for CIFAR10 -- Conclusion -- References -- Chapter 3: Autoencoders -- Principles of autoencoders -- Building autoencoders using Keras -- Denoising autoencoder (DAE) -- Automatic colorization autoencoder -- Conclusion -- References -- Chapter 4: Generative Adversarial Networks (GANs) -- An overview of GANs -- Principles of GANs -- GAN implementation in Keras -- Conditional GAN -- Conclusion -- References -- Chapter 5: Improved GANs -- Wasserstein GAN -- Distance functions -- Distance function in GANs -- Use of Wasserstein loss -- WGAN implementation using Keras -- Least-squares GAN (LSGAN) -- Auxiliary classifier GAN (ACGAN) -- Conclusion -- References -- Chapter 6: Disentangled Representation GANs -- Disentangled representations -- InfoGAN -- Implementation of InfoGAN in Keras -- Generator outputs of InfoGAN -- StackedGAN -- Implementation of StackedGAN in Keras.
Generator outputs of StackedGAN -- Conclusion -- Reference -- Chapter 7: Cross-Domain GANs -- Principles of CycleGAN -- The CycleGAN Model -- Implementing CycleGAN using Keras -- Generator outputs of CycleGAN -- CycleGAN on MNIST and SVHN datasets -- Conclusion -- References -- Chapter 8: Variational Autoencoders (VAEs) -- Principles of VAEs -- Variational inference -- Core equation -- Optimization -- Reparameterization trick -- Decoder testing -- VAEs in Keras -- Using CNNs for VAEs -- Conditional VAE (CVAE) -- -VAE: VAE with disentangled latent representations -- Conclusion -- References -- Chapter 9: Deep Reinforcement Learning -- Principles of reinforcement learning (RL) -- The Q value -- Q-Learning example -- Q-Learning in Python -- Nondeterministic environment -- Temporal-difference learning -- Q-Learning on OpenAI gym -- Deep Q-Network (DQN) -- DQN on Keras -- Double Q-Learning (DDQN) -- Conclusion -- References -- Chapter 10: Policy Gradient Methods -- Policy gradient theorem -- Monte Carlo policy gradient (REINFORCE) method -- REINFORCE with baseline method -- Actor-Critic method -- Advantage Actor-Critic (A2C) method -- Policy Gradient methods with Keras -- Performance evaluation of policy gradient methods -- Conclusion -- References -- Other Books You May Enjoy -- Index. |
Record Nr. | UNINA-9910819310903321 |
Atienza Rowel
![]() |
||
London, England : , : Packt Publishing, Limited, , [2018] | ||
![]() | ||
Lo trovi qui: Univ. Federico II | ||
|
Advanced deep learning with TensorFlow 2 and Keras : apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more / / Rowel Atienza |
Autore | Atienza Rowel |
Edizione | [Second edition.] |
Pubbl/distr/stampa | Birmingham, UK : , : Packt Publishing, , 2020 |
Descrizione fisica | 1 online resource (1 volume) : illustrations |
Soggetto topico |
Artificial intelligence
Machine learning Python (Computer program language) Neural networks (Computer science) |
ISBN | 1-83882-572-X |
Formato | Materiale a stampa ![]() |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Record Nr. | UNINA-9910795281003321 |
Atienza Rowel
![]() |
||
Birmingham, UK : , : Packt Publishing, , 2020 | ||
![]() | ||
Lo trovi qui: Univ. Federico II | ||
|
Advanced deep learning with TensorFlow 2 and Keras : apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more / / Rowel Atienza |
Autore | Atienza Rowel |
Edizione | [Second edition.] |
Pubbl/distr/stampa | Birmingham, UK : , : Packt Publishing, , 2020 |
Descrizione fisica | 1 online resource (1 volume) : illustrations |
Soggetto topico |
Artificial intelligence
Machine learning Python (Computer program language) Neural networks (Computer science) |
ISBN | 1-83882-572-X |
Formato | Materiale a stampa ![]() |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Record Nr. | UNINA-9910826422303321 |
Atienza Rowel
![]() |
||
Birmingham, UK : , : Packt Publishing, , 2020 | ||
![]() | ||
Lo trovi qui: Univ. Federico II | ||
|