Deep Learning with Keras Glossary

A

• Activation functions in Deep Learning with Keras
• Activation layers in Deep Learning with Keras
• Adadelta in Deep Learning with Keras
• Adafactor in Deep Learning with Keras
• Adagrad in Deep Learning with Keras
• Adam in Deep Learning with Keras
• Adamax in Deep Learning with Keras
• AdamW in Deep Learning with Keras
• Attention layers in Deep Learning with Keras

B

• Backpropagation in Deep Learning with Keras
• BackupAndRestore in Deep Learning with Keras
• Base Callback class in Deep Learning with Keras
• Batch normalization in Deep Learning with Keras
• Batch size in Deep Learning with Keras
• Binary classification in Deep Learning with Keras

C

• Callbacks in Deep Learning with Keras
• Categorical classification in Deep Learning with Keras
• Character-level language modeling in Deep Learning with Keras
• Clustering in Deep Learning with Keras
• Convolution layers in Deep Learning with Keras
• Convolutional layers in Deep Learning with Keras
• Convolutional neural networks in Deep Learning with Keras
• Core layers in Deep Learning with Keras
• Cross-entropy loss in Deep Learning with Keras
• CSVLogger in Deep Learning with Keras

D

• Data augmentation in Deep Learning with Keras
• Deep belief networks in Deep Learning with Keras
• Dense layers in Deep Learning with Keras
• Dropout in Deep Learning with Keras
• Dropout regularization in Deep Learning with Keras

E

• Early stopping in Deep Learning with Keras
• EarlyStopping in Deep Learning with Keras
• Embedding layers in Deep Learning with Keras
• Embedding matrices in Deep Learning with Keras
• Encoder-decoder models in Deep Learning with Keras
• Epochs in Deep Learning with Keras
• Error backpropagation in Deep Learning with Keras

F

• Feedforward neural networks in Deep Learning with Keras
• Fine-tuning in Deep Learning with Keras
• Flatten in Deep Learning with Keras
• Ftrl in Deep Learning with Keras
• Fully connected layers in Deep Learning with Keras

G

• Gated recurrent units (GRUs) in Deep Learning with Keras
• Generative adversarial networks (GANs) in Deep Learning with Keras
• Gradient descent in Deep Learning with Keras
• Grid search in Deep Learning with Keras

H

• Hyperparameter tuning in Deep Learning with Keras

I

• Image recognition in Deep Learning with Keras
• Image segmentation in Deep Learning with Keras
• Inception in Deep Learning with Keras
• InceptionV3 in Deep Learning with Keras
• Inference time in Deep Learning with Keras
• Input shape in Deep Learning with Keras
• Instance normalization in Deep Learning with Keras
• Iterations in Deep Learning with Keras

K

• K-fold cross-validation in Deep Learning with Keras
• Keras in Deep Learning with Keras

L

• L1 regularization in Deep Learning with Keras
• L2 regularization in Deep Learning with Keras
• Label smoothing in Deep Learning with Keras
• LambdaCallback in Deep Learning with Keras
• Layer activations in Deep Learning with Keras
• Layer weight constraints in Deep Learning with Keras
• Layer weight initializers in Deep Learning with Keras
• Layer weight regularizers in Deep Learning with Keras
• LeakyReLU in Deep Learning with Keras
• Learning rate in Deep Learning with Keras
• Learning rate scheduling in Deep Learning with Keras
• LearningRateScheduler in Deep Learning with Keras
• Locally connected layers in Deep Learning with Keras
• Locally-connected layers in Deep Learning with Keras
• Long short-term memory (LSTM) in Deep Learning with Keras

M

• Max pooling in Deep Learning with Keras
• Mean squared error in Deep Learning with Keras
• Merging layers in Deep Learning with Keras
• Metrics in Deep Learning with Keras
• Mini-batch in Deep Learning with Keras
• Model checkpointing in Deep Learning with Keras
• Model ensembling in Deep Learning with Keras
• Model evaluation in Deep Learning with Keras
• Model saving/loading in Deep Learning with Keras
• ModelCheckpoint in Deep Learning with Keras
• Multi-GPU training in Deep Learning with Keras
• Multi-layer perceptron in Deep Learning with Keras

N

• Nadam in Deep Learning with Keras
• Natural language processing in Deep Learning with Keras
• Nesterov accelerated gradient in Deep Learning with Keras
• Normalization layers in Deep Learning with Keras

O

• Object detection in Deep Learning with Keras
• One-shot learning in Deep Learning with Keras
• Optimizers in Deep Learning with Keras
• Overfitting in Deep Learning with Keras
• Overfitting/Underfitting in Deep Learning with Keras

P

• Padding in Deep Learning with Keras
• Pooling in Deep Learning with Keras
• Pooling layers in Deep Learning with Keras
• Pre-trained models in Deep Learning with Keras
• Precision in Deep Learning with Keras
• Precision-Recall curve in Deep Learning with Keras
• Preprocessing layers in Deep Learning with Keras
• ProgbarLogger in Deep Learning with Keras
• PyTorch in Deep Learning with Keras

R

• Radam in Deep Learning with Keras
• Rectified linear unit (ReLU) in Deep Learning with Keras
• Recurrent layers in Deep Learning with Keras
• Recurrent neural networks in Deep Learning with Keras
• ReduceLROnPlateau in Deep Learning with Keras
• Regularization in Deep Learning with Keras
• Regularization layers in Deep Learning with Keras
• ReLU6 in Deep Learning with Keras
• RemoteMonitor in Deep Learning with Keras
• Reshaping layers in Deep Learning with Keras
• Residual networks in Deep Learning with Keras
• RMSprop in Deep Learning with Keras

S

• Sequence-to-sequence models in Deep Learning with Keras
• SGD in Deep Learning with Keras
• Sigmoid in Deep Learning with Keras
• Softmax in Deep Learning with Keras
• Spatial dropout in Deep Learning with Keras
• Stochastic gradient descent in Deep Learning with Keras
• Stochastic gradient descent with momentum in Deep Learning with Keras

T

• TensorBoard in Deep Learning with Keras
• Tensorflow in Deep Learning with Keras
• TerminateOnNaN in Deep Learning with Keras
• Text classification in Deep Learning with Keras
• The base Layer class in Deep Learning with Keras
• TimeDistributed layer. in Deep Learning with Keras
• Transfer learning in Deep Learning with Keras
• Transpose convolution in Deep Learning with Keras
• Triplet loss in Deep Learning with Keras

U

• Unsupervised learning in Deep Learning with Keras

V

• Validation split in Deep Learning with Keras
• Vanishing gradient problem in Deep Learning with Keras
• Variational autoencoders in Deep Learning with Keras
• VGG16 in Deep Learning with Keras

W

• Weight decay in Deep Learning with Keras
• Weight initialization. in Deep Learning with Keras
• Word embeddings in Deep Learning with Keras

X

• Xavier initialization in Deep Learning with Keras

Z

• Zero padding in Deep Learning with Keras