[coursera/dl&nn/week4]Deep Neural Network(summary&question)
Deep learning is an experiment base on hyperparameters.
I strongly encourage you to find a paper to write down forward and backward propagate.
You need to review how to compute the derivative of metrics.
Week4 Deep Neural Network
4.1 Deep L-layer neural network
n[0]=nx=3
, n[1]=5 , n[2]=5,
n[3]=3,
n[4]= n[L]=1
4.2 Forward Propagate in a Deep Network
We need a for-loop to compute these hidden layers.
compute lth layer neuron
vectorizing
4.3 Getting your matrix dimensions right
This is important for us to modify our bug.
for lth layer neuron in m training examples:
n[l]: num of neurons in lth layer
n[l-1]: num
of neurons in (l-1)th layer
Z.shape()=(n[l],m)
W.shape()=(n[l],n[l-1])
X.shape()=(n[l-1],m)
b.shape()=(n[l],m)
4.4 Why deep representations
small: small amount of hidden nurons
deep: large num of hidden layers
4.5 Building blocks of deep neural networks
The flow chat shows how deep neural networks propagate.
4.6 Forward and Backward Propagation
Backward:
vectorizing:
4.7 Hyperparameters
learning rate
#iterations
#hidden layer L
#hidden units
4.8 points: what does this have to do with the brain
mapping: x to y
question: