Index
A
Activation functions
Adadelta
Adagrad algorithm
Adam
Adjointmode
Artificial Intelligence (AI)
Autograd
Automatic differentiation
fundamentals
forward mode
implementation
operator overloading
reverse mode
source code transformation
hands-on with Autograd
numerical differentiation
symbolic differentiation
B
Backward difference method
Bernoulli distribution
Bidirectional RNN
Binary classification
Binary cross entropy
C
Central difference approach
Composite functions
Computational graph
Computationally heavy code
Compute-intensive code
Constant error carousal
Convolution-detector-pooling block
Convolution Neural Networks (CNNs)
convolution-detector-pooling block
intuition
operation
fully connected layers
intuition
one dimension
sparse interactions in layer
tied weights ...
Get Deep Learning with Python: A Hands-on Introduction now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.