Deep Neural
Networks
Deep L-layer
[Link] Neural network
What is a deep neural network?
logistic regression 1 hidden layer
2 hidden layers 5 hidden layers
Andrew
Ng
Deep neural network notation
Andrew
Ng
Deep Neural
Networks
Forward Propagation
[Link] in a Deep Network
Forward propagation in a deep network
Andrew
Ng
Deep Neural
Networks
Getting your matrix
[Link]
dimensions right
Parameters ! ["] and " ["]
&!
$%
&"
Andrew Ng
Vectorized implementation
#!
!"
#"
Andrew Ng
Deep Neural
Networks
Why deep
[Link]
representations?
Intuition about deep representation
!"
Andrew Ng
Circuit theory and deep learning
Informally: There are functions you can compute with a
“small” L-layer deep neural network that shallower networks
require exponentially more hidden units to compute.
Andrew Ng
Deep Neural
Networks
Building blocks of
[Link] deep neural networks
Forward and backward functions
Andrew
Ng
Forward and backward functions
Andrew
Ng
Deep Neural
Networks
Parameters vs
[Link]
Hyperparameters
What are hyperparameters?
Parameters: ! " , % " ,! & ,% & ,! ' ,% ' …
Andrew Ng
Applied deep learning is a very
empirical process
Idea
cost !
Experiment Code # of iterations
Andrew Ng
Deep Neural
Networks
What does this
[Link] have to do with
the brain?
Forward and backward propagation
! ["] = # ["] $ + & ["] -! [%] = '[%] − +
1
'["] = ( " (! " ) -# [%] = -! % ' %
&
0
! [$] = # [$] '["] + & [$] 1
'[$] = ( $ (! $ ) -& [%] = 12. sum(d! % , 9:;< = 1, =>>2-;0< = ?@A>)
0 & %
-! [%'"] = -# % -! % (( (! %'" )
…
'[%] = ( % ! % = +,
…
& "
-! ["] = -# % -! $ (( (! " )
1 &
-# = -! " ' "
["]
0
1
-& = 12. sum(d! " , 9:;< = 1, =>>2-;0< = ?@A>)
["]
0
Andrew Ng
