Index
A
- AdaDelta
- used, for optimization / Optimization with AdaDelta, Adadelta optimizer
- adaptive moment estimation (Adam)
- used, for optimization / Optimization with Adam, How to do it...
- about / Modeling, Instantiate a sequential model, Instantiate a sequential model
- advantage network / Dueling DQN to play Cartpole
- Artificial Intelligence (AI) / Introduction
B
- Basic Linear Algebra Subprograms (BLAS) /
- batch size / Without embeddings, With embeddings, How to do it…
- BoltzmannQPolicy
- about / BoltzmannQPolicy
- training / Adjustment during training
- boundary seeking GAN (BGAN)
- about / Boundary seeking GAN, Getting ready
- generator / Generator
- discriminator / Discriminator
- class, initializing / Initializing the BGAN class
- training / Train the BGAN
- output plots / Output the plots
- iteration / Iteration 10000
- metrics / Metrics of the BGAN model
- metrics, plotting / Plotting the metrics
- breast cancer
- classification / Classification for breast cancer, How to do it...
- data processing / Data processing
- modeling / Modeling
- full code listing / Full code listing
C
- CartPole game
- with Keras / The CartPole game with Keras
- DQN agent, implementing / Implementing the DQN agent
- memory / The memory and remember
- replay function / The replay function
- act function / The act function
- hyperparameters, for DQN agent / Hyperparameters for the DQN
- DQN agent class / DQN agent class
- DQN agent, training / Training the agent
- cervical cancer
- classifying / Getting ready
- data processing / Data processing
- modeling / Modeling
- predictions / Predictions
- cervix type classification
- reference / Getting ready
- CIFAR-10 dataset
- exploring / CIFAR-10 dataset, How to do it...
- reference / CIFAR-10 dataset
- CIFAR-100 dataset
- exploring / CIFAR-100 dataset, How to do it...
- download link / How to do it...
- label mode, specifying / Specifying the label mode
- Conda / Installing Keras on Ubuntu 16.04
- convolutional neural networks (CNNs) / Introduction
- CSV file
- data, loading from / Load data from a CSV file
- cuda
- installing / Installing cuda
- cudann
- installing / Installing cudnn
D
- DCGAN
- about / DCGAN
- architecture guidelines / DCGAN
- generator / Generator, Summary of the generator
- discriminator / Discriminator, Summary of the discriminator
- build discriminator / Build the discriminator
- discriminator, compiling / Compile the discriminator
- combined model, creating / Combined model - generator and discriminator
- generator, training with feedback from discriminator / Train the generator using feedback from a discriminator
- program output / The output of the program
- model, average metrics / Average metrics of the model
- Deep Q Network (DQN) / Introduction
- deep reinforcement learning / Introduction
- diagnosis / Data processing
- Digit recognition MNIST dataset
- about / Digit recognition, How to do it…
- modeling / Modeling
- discriminator / Introduction
- Docker CLI
- URL / Getting ready
- Docker container
- installing / Installing the Docker container
- installing, with host volume mapped / Installing the Docker container with the host volume mapped
- Docker image
- Keras, installing with Jupyter Notebook / Installing Keras with Jupyter Notebook in a Docker image
- DQN agent
- about / DQN agent
- init method / init method
- Dueling DQN network
- about / Dueling DQN to play Cartpole
- to Cartpole game / Dueling DQN to play Cartpole
- testing results, plotting / Plotting the training and testing results
- training results, plotting / Plotting the training and testing results
- dueling policies
- about / Dueling policy
- Eps greedy policy / Dueling policy
- softmax policy / Dueling policy
- linear annealed policy / Dueling policy
E
- embedding space / Word embedding
- epochs / Without embeddings, With embeddings, How to do it…
- epsilon / The act function
- exploration rate / The act function
- exponential linear unit (ELU) / Modeling
F
- fine needle aspirate (FNA) / Classification for breast cancer
G
- generative adversarial networks (GANs)
- about / Introduction, Basic GAN
- overview / GAN overview
- creating / Getting ready
- generator, building / Building a generator
- discriminator, building / Building a discriminator
- instance, initializing / Initialize the GAN instance
- training / Training the GAN
- output plots / Output plots
- average metrics / Average metrics of the GAN
- generator / Introduction
- Global Vectors for Word Representation (GloVe) / With embeddings
- Grand Old Party (GOP) / Getting ready
H
- hyperparameter optimization / Modeling
I
- image data
- feature standardization / Feature standardization of image data, How to do it...
- ImageDataGenerator, initializing / Initializing ImageDataGenerator
- init code base / Init code base
J
- Jupyter Notebook
- Keras, installing in Docker image / Installing Keras with Jupyter Notebook in a Docker image
K
- Keras
- installing, on Ubuntu / Installing Keras on Ubuntu 16.04
- miniconda, installing / Installing miniconda
- numpy, installing /
- scipy, installing /
- mkl, installing / Installing mkl
- TensorFlow, installing / Installing TensorFlow
- installing / Installing Keras, Installing Keras
- Theano backend, using / Using the Theano backend with Keras
- installing, with Jupyter Notebook in Docker image / Installing Keras with Jupyter Notebook in a Docker image
- installing, on Ubuntu 16.04 with GPU enabled / Installing Keras on Ubuntu 16.04 with GPU enabled, Getting ready, How to do it...
- cuda, installing / Installing cuda
- cudann, installing / Installing cudnn
- NVIDIA CUDA profiler tools interface development files, installing / Installing NVIDIA CUDA profiler tools interface development files
- TensorFlow GPU version, installing / Installing the TensorFlow GPU version
- model / Models in Keras – getting started
- used, for feature standardization of image data / Feature standardization of image data
- used, for sequence padding / Sequence padding
- used, for CartPole game / The CartPole game with Keras
- Keras functional APIs
- using / Keras functional APIs, How to do it...
- example output / The output of the example
- layers, linking / Keras functional APIs – linking the layers
- used, for image classification / Image classification using Keras functional APIs, How to do it...
L
- layers
- model class / Model class
- long term short term memory (LSTM)
- about / Introduction
- sequence to sequence learning / Sequence to sequence learning for the same length output with LSTM
- data, training / Training data
- model creation / Model creation
- model fit and prediction / Model fit and prediction
- LSTM networks
- for Time Series data / LSTM networks for time series data
- about / LSTM networks
- memory, example / LSTM memory example
- encoder / Encoder
- model / LSTM configuration and model
- configuration / LSTM configuration and model
- model, training / Train the model
- full code listing / Full code listing
M
- mean absolute error (MAE) / How to do it...
- mean square error (MSE) / Instantiate a sequential model, How to do it...
- memory / Simple RNNs for time series data, The memory and remember
- mkl
- installing / Installing mkl
- MNIST dataset
- file, references / MNIST dataset
- about / MNIST dataset
- IDX file format / MNIST dataset
- exploring / How to do it...
- model
- anatomy / Anatomy of a model
- types / Types of models
- visualizing / Model visualization
- code listing / Code listing
N
- natural language processing (NLP) / Introduction, Introduction
- Natural Language Toolkit (NLTK) / Data processing
- network layer
- setting / Setting the last layer of the network
- normalized exponential function / Model creation
- numpy
- installing /
- NVIDIA
- URL / Installing cuda, Installing cudnn
O
- optimization
- about / Optimization
- stochastic gradient descent (SGD), using / Optimization with stochastic gradient descent, How to do it...
- Adam, using / Optimization with Adam, How to do it...
- AdaDelta, using / Optimization with AdaDelta, How to do it..., Adadelta optimizer
- RMSProp, using / Optimization with RMSProp, How to do it...
P
- parameters / Modeling
Q
- Q function / Introduction
R
- recurrent neural network (RNN)
- about / Introduction, Text summarization for reviews
- need for / The need for RNNs
- for time series data / Simple RNNs for time series data, How to do it…
- dataset, loading / Loading the dataset
- sequential model, instantiate / Instantiate a sequential model
- RMSProp
- used, for optimization / Optimization with RMSProp, How to do it...
S
- samples
- code / Common code for samples
- scipy
- installing /
- sentiment analysis
- about / Sentiment analysis, How to do it…
- full code listing / Full code listing
- sequence-to-sequence (seq2seq) / Text summarization for reviews
- sequence padding
- using / Sequence padding
- pre-padding, with default 0.0 padding / Pre-padding with default 0.0 padding
- post-padding / Post-padding
- truncation, using / Padding with truncation
- non-default value, using / Padding with a non-default value
- sequential memory
- about / Sequential memory
- observations (dict) / Sequential memory
- actions (int) / Sequential memory
- rewards (float) / Sequential memory
- terminals (Boolean) / Sequential memory
- sequential models
- about / Sequential models
- compiling / Compile the model
- training / Train the model , Model training
- evaluating / Evaluate the model
- predicting / Predict using the model
- diabetes dataset, using / Putting it all together
- inspection internals / Model inspection internals
- compilation internals / Model compilation internals
- loss, initializing / Initialize the loss
- sample output / Output of the sample
- shared input layer
- using / Introduction – shared input layer
- concatenate function / Concatenate function
- shared layer models
- about / Shared layer models
- shared input layer / Introduction – shared input layer
- spam detection
- classification / Classification for spam detection, How to do it...
- data processing / Data processing
- modeling / Modeling
- full code listing / Full code listing
- state network / Dueling DQN to play Cartpole
- stochastic gradient descent (SGD)
- used, for optimization / Optimization with stochastic gradient descent, How to do it...
T
- TensorFlow
- installing / Installing TensorFlow
- test set / How to do it…
- text summarization
- for reviews / Text summarization for reviews
- data processing / Data processing
- encoder-decoder architecture / Encoder-decoder architecture
- training / Training
- Time series forecasting
- with LSTM / Time series forecasting with LSTM, How to do it…
- dataset, loading / Load the dataset
- sequential model, instantiate / Instantiate a sequential model
- observation / Observation
- tokenization / Data processing, How to do it…
- tokens / Data processing, How to do it…
- training set / How to do it…
U
- Ubuntu
- Keras, installing / Installing Keras on Ubuntu 16.04
- Ubuntu 16.04
- Keras, installing with GPU enabled / Installing Keras on Ubuntu 16.04 with GPU enabled, Getting ready, How to do it...
W
- Word embedding
- about / Word embedding
- without embeddings / Without embeddings
- with embeddings / With embeddings
- word to vector (Word2Vec) / Word embedding