<h2 id=”t

# Building Deep Neural Network: Step by Step I

We have previously trained a 2-layer Neural Network (with a single hidden layer). In this notebook, we will build a deep neural network, with as many layers as we want!

In this notebook:

• I will implement all the functions required to build a deep neural network.
• In the next notebook, I will use these functions to build a deep neural network for image classification.

Goals of this Notebook are to:

• Use non-linear units like ReLU to improve your model
• Build a deeper neural network (with more than 1 hidden layer)
• Implement an easy-to-use neural network class

Notation:

• Superscript $[l]$ denotes a quantity associated with the $l^{th}$ layer.
• Example: $a^{[L]}$ is the $L^{th}$ layer activation. $W^{[L]}$ and $b^{[L]}$ are the $L^{th}$ layer parameters.
• Superscript $(i)$ denotes a quantity associated with the $i^{th}$ example.
• Example: $x^{(i)}$ is the $i^{th}$ training example.
• Lowerscript $i$ denotes the $i^{th}$ entry of a vector.
• Example: $a^{[l]}_i$ denotes the $i^{th}$ entry of the $l^{th}$ layer’s activations).

Let’s get started!

## 1 - Packages

Let’s first import all the packages that I will use in the notebook.

• numpy is the main package for scientific computing with Python.
• matplotlib is a library to plot graphs in Python.
• dnn_utils provides some necessary functions for this notebook.
• testCases provides some test cases to assess the correctness of our functions
• np.random.seed(1) is used to keep all the random function calls consistent.
import numpy as np
import h5py
import matplotlib.pyplot as plt
from testCases_v4 import *
from dnn_utils_v2 import sigmoid, sigmoid_backward, relu, relu_backward

%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

np.random.seed(1)

The autoreload extension is already loaded. To reload it, use:


## 2 - Outline of this Notebook

To build our neural network, I will be implementing several “helper functions”. These helper functions will be used in the next notebook to build a two-layer neural network and an L-layer neural network. Here is an outline of the helper functions, I will:

• Initialise the parameters for a two-layer network and for an $L$-layer neural network.
• Implement the forward propagation module (shown in purple in the figure below).
• Complete the LINEAR part of a layer’s forward propagation step (resulting in $Z^{[l]}$).
• The ACTIVATION function (relu/sigmoid) will be provided.
• Combine the previous two steps into a new [LINEAR->ACTIVATION] forward function.
• Stack the [LINEAR->RELU] forward function L-1 time (for layers 1 through L-1) and add a [LINEAR->SIGMOID] at the end (for the final layer $L$). This gives me a new L_model_forward function.
• Compute the loss.
• Implement the backward propagation module (denoted in red in the figure below).
• Complete the LINEAR part of a layer’s backward propagation step.
• The gradient of the ACTIVATE function (relu_backward/sigmoid_backward) will be provided.
• Combine the previous two steps into a new [LINEAR->ACTIVATION] backward function.
• Stack [LINEAR->RELU] backward L-1 times and add [LINEAR->SIGMOID] backward in a new L_model_backward function
• Finally update the parameters.

**Figure 1**

Note: for every forward function, there is a corresponding backward function. That is why at every step of my forward module I will be storing some values in a cache. The cached values are useful for computing gradients. In the backpropagation module you will then use the cache to calculate the gradients.

## 3 - Initialisation

I will write two helper functions that will initialise the parameters for our model. The first function will be used to initialise parameters for a two layer model. The second one will generalise this initialisation process to $L$ layers.

### 3.1 - 2-layer Neural Network

Now let’s create and initialise the parameters of the 2-layer neural network.

The following cell will do:

• The model’s structure is: LINEAR -> RELU -> LINEAR -> SIGMOID.
• Use random initialisation for the weight matrices. Use np.random.randn(shape)*0.01 with the correct shape.
• Use zero initialisation for the biases. Use np.zeros(shape).
def initialise_parameters(n_x, n_h, n_y):
"""
Argument:
n_x -- size of the input layer
n_h -- size of the hidden layer
n_y -- size of the output layer

Returns:
parameters -- python dictionary containing your parameters:
W1 -- weight matrix of shape (n_h, n_x)
b1 -- bias vector of shape (n_h, 1)
W2 -- weight matrix of shape (n_y, n_h)
b2 -- bias vector of shape (n_y, 1)
"""

np.random.seed(1)
W1 = np.random.randn(n_h, n_x)*0.01
b1 = np.zeros(shape=(n_h, 1))
W2 = np.random.randn(n_y, n_h)*0.01
b2 = np.zeros(shape=(n_y, 1))

assert(W1.shape == (n_h, n_x))
assert(b1.shape == (n_h, 1))
assert(W2.shape == (n_y, n_h))
assert(b2.shape == (n_y, 1))

parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}

return parameters

parameters = initialise_parameters(3,2,1)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))

W1 = [[ 0.01624345 -0.00611756 -0.00528172]
[-0.01072969  0.00865408 -0.02301539]]
b1 = [[ 0.]
[ 0.]]
W2 = [[ 0.01744812 -0.00761207]]
b2 = [[ 0.]]


### 3.2 - L-layer Neural Network

The initialisation for a deeper L-layer neural network is more complicated because there are many more weight matrices and bias vectors. When completing the initialise_parameters_deep, we should make sure that our dimensions match between each layer. Recall that $n^{[l]}$ is the number of units in layer $l$. Thus for example if the size of our input $X$ is $(12288, 209)$ (with $m=209$ examples) then:

</table> Remember that when we compute $W X + b$ in python, it carries out broadcasting. For example, if: $$W = \begin{bmatrix} j & k & l\\ m & n & o \\ p & q & r \end{bmatrix}\;\;\; X = \begin{bmatrix} a & b & c\\ d & e & f \\ g & h & i \end{bmatrix} \;\;\; b =\begin{bmatrix} s \\ t \\ u \end{bmatrix}\tag{2}$$ Then $WX + b$ will be: $$WX + b = \begin{bmatrix} (ja + kd + lg) + s & (jb + ke + lh) + s & (jc + kf + li)+ s\\ (ma + nd + og) + t & (mb + ne + oh) + t & (mc + nf + oi) + t\\ (pa + qd + rg) + u & (pb + qe + rh) + u & (pc + qf + ri)+ u \end{bmatrix}\tag{3}$$ Now let's implement initialisation for an L-layer Neural Network. **The following cell will do:** - The model's structure is *[LINEAR -> RELU] $\times$ (L-1) -> LINEAR -> SIGMOID*. I.e., it has $L-1$ layers using a ReLU activation function followed by an output layer with a sigmoid activation function. - Use random initialisation for the weight matrices. Use np.random.randn(shape) * 0.01. - Use zeros initialisation for the biases. Use np.zeros(shape). - We will store $n^{[l]}$, the number of units in different layers, in a variable layer_dims. For example, the layer_dims for the "Planar Data classification model" from last week would have been [2,4,1]: There were two inputs, one hidden layer with 4 hidden units, and an output layer with 1 output unit. This means W1's shape was (4,2), b1 was (4,1), W2 was (1,4) and b2 was (1,1). Now we will generalise this to $L$ layers! - Here is the implementation for $L=1$ (one layer neural network). It should inspire us to implement the general case (L-layer neural network). python if L == 1: parameters["W" + str(L)] = np.random.randn(layer_dims[1], layer_dims[0]) * 0.01 parameters["b" + str(L)] = np.zeros((layer_dims[1], 1))  python def initialise_parameters_deep(layer_dims): """ Arguments: layer_dims -- python array (list) containing the dimensions of each layer in our network Returns: parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL": Wl -- weight matrix of shape (layer_dims[l], layer_dims[l-1]) bl -- bias vector of shape (layer_dims[l], 1) """ np.random.seed(3) parameters = {} L = len(layer_dims) # number of layers in the network for l in range(1, L): parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l - 1])*0.01 parameters['b' + str(l)] = np.zeros((layer_dims[l], 1)) assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l-1])) assert(parameters['b' + str(l)].shape == (layer_dims[l], 1)) return parameters  python parameters = initialise_parameters_deep([5,4,3]) print("W1 = " + str(parameters["W1"])) print("b1 = " + str(parameters["b1"])) print("W2 = " + str(parameters["W2"])) print("b2 = " + str(parameters["b2"]))  W1 = [[ 0.01788628 0.0043651 0.00096497 -0.01863493 -0.00277388] [-0.00354759 -0.00082741 -0.00627001 -0.00043818 -0.00477218] [-0.01313865 0.00884622 0.00881318 0.01709573 0.00050034] [-0.00404677 -0.0054536 -0.01546477 0.00982367 -0.01101068]] b1 = [[ 0.] [ 0.] [ 0.] [ 0.]] W2 = [[-0.01185047 -0.0020565 0.01486148 0.00236716] [-0.01023785 -0.00712993 0.00625245 -0.00160513] [-0.00768836 -0.00230031 0.00745056 0.01976111]] b2 = [[ 0.] [ 0.] [ 0.]] ## 4 - Forward propagation module ### 4.1 - Linear Forward Now that we have initialised our parameters, we will do the forward propagation module. We will start by implementing some basic functions that we will use later when implementing the model. - LINEAR - LINEAR -> ACTIVATION where ACTIVATION will be either ReLU or Sigmoid. - [LINEAR -> RELU] $\times$ (L-1) -> LINEAR -> SIGMOID (whole model) The linear forward module (vectorised over all the examples) computes the following equations: $$Z^{[l]} = W^{[l]}A^{[l-1]} +b^{[l]}\tag{4}$$ where $A^{[0]} = X$. Let's build the linear part of forward propagation. **Note: ** The mathematical representation of this unit is $Z^{[l]} = W^{[l]}A^{[l-1]} +b^{[l]}$. We will use np.dot() for dot product of two arrays and W.shape to check dimensions of the array. python def linear_forward(A, W, b): """ Implement the linear part of a layer's forward propagation. Arguments: A -- activations from previous layer (or input data): (size of previous layer, number of examples) W -- weights matrix: numpy array of shape (size of current layer, size of previous layer) b -- bias vector, numpy array of shape (size of the current layer, 1) Returns: Z -- the input of the activation function, also called pre-activation parameter cache -- a python tuple containing "A", "W" and "b" ; stored for computing the backward pass efficiently """ Z = np.dot(W, A)+b assert(Z.shape == (W.shape[0], A.shape[1])) cache = (A, W, b) return Z, cache  python A, W, b = linear_forward_test_case() Z, linear_cache = linear_forward(A, W, b) print("Z = " + str(Z))  Z = [[ 3.26295337 -1.23429987]] ### 4.2 - Linear-Activation Forward In this notebook, we will use two activation functions: - **Sigmoid**: $\sigma(Z) = \sigma(W A + b) = \frac{1}{ 1 + e^{-(W A + b)}}$. The sigmoid function is provided. This function returns **two** items: the activation value "a" and a "cache" that contains "Z" (it's what we will feed in to the corresponding backward function). To use it we can just call:  python A, activation_cache = sigmoid(Z)  - **ReLU**: The mathematical formula for ReLu is $A = RELU(Z) = max(0, Z)$. The relu function si also provided. This function returns **two** items: the activation value "A" and a "cache" that contains "Z" (it's what we will feed in to the corresponding backward function). To use itwe can just call:  python A, activation_cache = relu(Z)  For more convenience, we are going to group two functions (Linear and Activation) into one function (LINEAR->ACTIVATION). Hence, we will implement a function that does the LINEAR forward step followed by an ACTIVATION forward step. **The following cell will: ** Implement the forward propagation of the *LINEAR->ACTIVATION* layer. Mathematical relation is: $A^{[l]} = g(Z^{[l]}) = g(W^{[l]}A^{[l-1]} +b^{[l]})$ where the activation "g" can be sigmoid() or relu(). Use linear_forward() and the correct activation function. python def linear_activation_forward(A_prev, W, b, activation): """ Implement the forward propagation for the LINEAR->ACTIVATION layer Arguments: A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples) W -- weights matrix: numpy array of shape (size of current layer, size of previous layer) b -- bias vector, numpy array of shape (size of the current layer, 1) activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu" Returns: A -- the output of the activation function, also called the post-activation value cache -- a python tuple containing "linear_cache" and "activation_cache"; stored for computing the backward pass efficiently """ if activation == "sigmoid": # Inputs: "A_prev, W, b". Outputs: "A, activation_cache". Z, linear_cache = linear_forward(A_prev, W, b) A, activation_cache = sigmoid(Z) elif activation == "relu": # Inputs: "A_prev, W, b". Outputs: "A, activation_cache". Z, linear_cache = linear_forward(A_prev, W, b) A, activation_cache = relu(Z) assert (A.shape == (W.shape[0], A_prev.shape[1])) cache = (linear_cache, activation_cache) return A, cache  python A_prev, W, b = linear_activation_forward_test_case() A, linear_activation_cache = linear_activation_forward(A_prev, W, b, activation = "sigmoid") print("With sigmoid: A = " + str(A)) A, linear_activation_cache = linear_activation_forward(A_prev, W, b, activation = "relu") print("With ReLU: A = " + str(A))  With sigmoid: A = [[ 0.96890023 0.11013289]] With ReLU: A = [[ 3.43896131 0. ]] **Note**: In deep learning, the "[LINEAR->ACTIVATION]" computation is counted as a single layer in the neural network, not two layers. ### d) L-Layer Model For even more convenience when implementing the $L$-layer Neural Net, we will need a function that replicates the previous one (linear_activation_forward with RELU) $L-1$ times, then follows that with one linear_activation_forward with SIGMOID.
Now let's implement the forward propagation of the above model. **In the cell below will: ** The variable AL will denote $A^{[L]} = \sigma(Z^{[L]}) = \sigma(W^{[L]} A^{[L-1]} + b^{[L]})$. (This is sometimes also called Yhat, i.e., this is $\hat{Y}$.) **Tricks**: - Use the functions we had previously written - Use a for loop to replicate [LINEAR->RELU] (L-1) times - Don't forget to keep track of the caches in the "caches" list. To add a new value c to a list, we can use list.append(c). python def L_model_forward(X, parameters): """ Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation Arguments: X -- data, numpy array of shape (input size, number of examples) parameters -- output of initialise_parameters_deep() Returns: AL -- last post-activation value caches -- list of caches containing: every cache of linear_activation_forward() (there are L-1 of them, indexed from 0 to L-1) """ caches = [] A = X L = len(parameters) // 2 # number of layers in the neural network # Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list. for l in range(1, L): A_prev = A A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], activation='relu') caches.append(cache) # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list. AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], activation='sigmoid') caches.append(cache) assert(AL.shape == (1,X.shape[1])) return AL, caches  python X, parameters = L_model_forward_test_case_2hidden() AL, caches = L_model_forward(X, parameters) print("AL = " + str(AL)) print("Length of caches list = " + str(len(caches)))  AL = [[ 0.03921668 0.70498921 0.19734387 0.04728177]] Length of caches list = 3 Yay! We now have a full forward propagation that takes the input X and outputs a row vector $A^{[L]}$ containing our predictions. It also records all intermediate values in "caches". Using $A^{[L]}$, we can compute the cost of our predictions. ## 5 - Cost function Now we will implement forward and backward propagation. We need to compute the cost, because we want to check if our model is actually learning. **The following cell will: ** Compute the cross-entropy cost $J$, using the following formula: $$-\frac{1}{m} \sum\limits_{i = 1}^{m} (y^{(i)}\log\left(a^{[L] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[L](i)}\right)) \tag{7}$$ python def compute_cost(AL, Y): """ Implement the cost function defined by equation (7). Arguments: AL -- probability vector corresponding to your label predictions, shape (1, number of examples) Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples) Returns: cost -- cross-entropy cost """ m = Y.shape[1] # Compute loss from aL and y. cost = (-1 / m) * np.sum(np.multiply(Y, np.log(AL)) + np.multiply(1 - Y, np.log(1 - AL))) cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17). assert(cost.shape == ()) return cost  python Y, AL = compute_cost_test_case() print("cost = " + str(compute_cost(AL, Y)))  cost = 0.414931599615 ## 6 - Backward propagation module Just like with forward propagation, I will implement helper functions for backpropagation and recall that back propagation is used to calculate the gradient of the loss function with respect to the parameters. **Reminder**: Now, similar to forward propagation, I am going to build the backward propagation in three steps: - LINEAR backward - LINEAR -> ACTIVATION backward where ACTIVATION computes the derivative of either the ReLU or sigmoid activation - [LINEAR -> RELU] $\times$ (L-1) -> LINEAR -> SIGMOID backward (whole model) ### 6.1 - Linear backward For layer $l$, the linear part is: $Z^{[l]} = W^{[l]} A^{[l-1]} + b^{[l]}$ (followed by an activation). After we have already calculated the derivative $dZ^{[l]} = \frac{\partial \mathcal{L} }{\partial Z^{[l]}}$, we want to get $(dW^{[l]}, db^{[l]} dA^{[l-1]})$. The three outputs $(dW^{[l]}, db^{[l]}, dA^{[l]})$ are computed using the input $dZ^{[l]}$. Here are the formulas we need: $$dW^{[l]} = \frac{\partial \mathcal{L} }{\partial W^{[l]}} = \frac{1}{m} dZ^{[l]} A^{[l-1] T} \tag{8}$$ $$db^{[l]} = \frac{\partial \mathcal{L} }{\partial b^{[l]}} = \frac{1}{m} \sum_{i = 1}^{m} dZ^{[l](i)}\tag{9}$$ $$dA^{[l-1]} = \frac{\partial \mathcal{L} }{\partial A^{[l-1]}} = W^{[l] T} dZ^{[l]} \tag{10}$$ Let's use the 3 formulas above to implement linear_backward(). python def linear_backward(dZ, cache): """ Implement the linear portion of backward propagation for a single layer (layer l) Arguments: dZ -- Gradient of the cost with respect to the linear output (of current layer l) cache -- tuple of values (A_prev, W, b) coming from the forward propagation in the current layer Returns: dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev dW -- Gradient of the cost with respect to W (current layer l), same shape as W db -- Gradient of the cost with respect to b (current layer l), same shape as b """ A_prev, W, b = cache m = A_prev.shape[1] dW = 1./m*np.dot(dZ, A_prev.T) db = 1./m*np.sum(dZ, axis = 1, keepdims=True) dA_prev = np.dot(W.T, dZ) assert (dA_prev.shape == A_prev.shape) assert (dW.shape == W.shape) assert (db.shape == b.shape) return dA_prev, dW, db  python # Set up some test inputs dZ, linear_cache = linear_backward_test_case() dA_prev, dW, db = linear_backward(dZ, linear_cache) print ("dA_prev = "+ str(dA_prev)) print ("dW = " + str(dW)) print ("db = " + str(db))  dA_prev = [[ 0.51822968 -0.19517421] [-0.40506361 0.15255393] [ 2.37496825 -0.89445391]] dW = [[-0.10076895 1.40685096 1.64992505]] db = [[ 0.50629448]] ### 6.2 - Linear-Activation backward Next, I will create a function that merges the two helper functions: **linear_backward** and the backward step for the activation **linear_activation_backward**. Two backward functions are provided to help you implement linear_activation_backward,: - **sigmoid_backward**: Implements the backward propagation for SIGMOID unit. It can be called as follows: python dZ = sigmoid_backward(dA, activation_cache)  - **relu_backward**: Implements the backward propagation for RELU unit. It can be called as follows: python dZ = relu_backward(dA, activation_cache)  If $g(.)$ is the activation function, sigmoid_backward and relu_backward compute $$dZ^{[l]} = dA^{[l]} * g'(Z^{[l]}) \tag{11}$$. **The following cell will: ** Implement the backpropagation for the *LINEAR->ACTIVATION* layer. python def linear_activation_backward(dA, cache, activation): """ Implement the backward propagation for the LINEAR->ACTIVATION layer. Arguments: dA -- post-activation gradient for current layer l cache -- tuple of values (linear_cache, activation_cache) we store for computing backward propagation efficiently activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu" Returns: dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev dW -- Gradient of the cost with respect to W (current layer l), same shape as W db -- Gradient of the cost with respect to b (current layer l), same shape as b """ linear_cache, activation_cache = cache if activation == "relu": dZ = relu_backward(dA, activation_cache) dA_prev, dW, db = linear_backward(dZ, linear_cache) elif activation == "sigmoid": dZ = sigmoid_backward(dA, activation_cache) dA_prev, dW, db = linear_backward(dZ, linear_cache) return dA_prev, dW, db  python dAL, linear_activation_cache = linear_activation_backward_test_case() dA_prev, dW, db = linear_activation_backward(dAL, linear_activation_cache, activation = "sigmoid") print ("sigmoid:") print ("dA_prev = "+ str(dA_prev)) print ("dW = " + str(dW)) print ("db = " + str(db) + "\n") dA_prev, dW, db = linear_activation_backward(dAL, linear_activation_cache, activation = "relu") print ("relu:") print ("dA_prev = "+ str(dA_prev)) print ("dW = " + str(dW)) print ("db = " + str(db))  sigmoid: dA_prev = [[ 0.11017994 0.01105339] [ 0.09466817 0.00949723] [-0.05743092 -0.00576154]] dW = [[ 0.10266786 0.09778551 -0.01968084]] db = [[-0.05729622]] relu: dA_prev = [[ 0.44090989 -0. ] [ 0.37883606 -0. ] [-0.2298228 0. ]] dW = [[ 0.44513824 0.37371418 -0.10478989]] db = [[-0.20837892]] ### 6.3 - L-Model Backward Now we will implement the backward function for the whole network. Recall that when we implemented the L_model_forward function, at each iteration, we stored a cache which contains (X,W,b, and z). In the back propagation module, we will use those variables to compute the gradients. Therefore, in the L_model_backward function, we will iterate through all the hidden layers backward, starting from layer $L$. On each step, we will use the cached values for layer $l$ to backpropagate through layer $l$. Figure 5 below shows the backward pass. ** Initializing backpropagation**: To backpropagate through this network, we know that the output is, $A^{[L]} = \sigma(Z^{[L]})$. Our code thus needs to compute dAL $= \frac{\partial \mathcal{L}}{\partial A^{[L]}}$. To do so, use this formula: python dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL)) # derivative of cost with respect to AL  We can then use this post-activation gradient dAL to keep going backward. As seen in Figure 5, we can now feed in dAL into the LINEAR->SIGMOID backward function we implemented (which will use the cached values stored by the L_model_forward function). After that, we will have to use a for loop to iterate through all the other layers using the LINEAR->RELU backward function. We should store each dA, dW, and db in the grads dictionary. To do so, we will use this formula : $$grads["dW" + str(l)] = dW^{[l]}\tag{15}$$ For example, for $l=3$ this would store $dW^{[l]}$ in grads["dW3"]. **The following cell will:** Implement backpropagation for the *[LINEAR->RELU] $\times$ (L-1) -> LINEAR -> SIGMOID* model. python def L_model_backward(AL, Y, caches): """ Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group Arguments: AL -- probability vector, output of the forward propagation (L_model_forward()) Y -- true "label" vector (containing 0 if non-cat, 1 if cat) caches -- list of caches containing: every cache of linear_activation_forward() with "relu" (it's caches[l], for l in range(L-1) i.e l = 0...L-2) the cache of linear_activation_forward() with "sigmoid" (it's caches[L-1]) Returns: grads -- A dictionary with the gradients grads["dA" + str(l)] = ... grads["dW" + str(l)] = ... grads["db" + str(l)] = ... """ grads = {} L = len(caches) # the number of layers m = AL.shape[1] Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL # Initializing the backpropagation dAL = -(np.divide(Y, AL)-np.divide(1-Y, 1-AL)) # Lth layer (SIGMOID -> LINEAR) gradients. Inputs: "dAL, current_cache". Outputs: "grads["dAL-1"], grads["dWL"], grads["dbL"] current_cache = caches[L-1] grads["dA" + str(L-1)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dAL, current_cache, activation = "sigmoid") # Loop from l=L-2 to l=0 for l in reversed(range(L-1)): # lth layer: (RELU -> LINEAR) gradients. # Inputs: "grads["dA" + str(l + 1)], current_cache". Outputs: "grads["dA" + str(l)] , grads["dW" + str(l + 1)] , grads["db" + str(l + 1)] current_cache = caches[l] dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l+1)], current_cache, activation = "relu") grads["dA" + str(l)] = dA_prev_temp grads["dW" + str(l + 1)] = dW_temp grads["db" + str(l + 1)] = db_temp return grads  python AL, Y_assess, caches = L_model_backward_test_case() grads = L_model_backward(AL, Y_assess, caches) print_grads(grads)  dW1 = [[ 0.41010002 0.07807203 0.13798444 0.10502167] [ 0. 0. 0. 0. ] [ 0.05283652 0.01005865 0.01777766 0.0135308 ]] db1 = [[-0.22007063] [ 0. ] [-0.02835349]] dA1 = [[ 0.12913162 -0.44014127] [-0.14175655 0.48317296] [ 0.01663708 -0.05670698]] ### 6.4 - Update Parameters In this section we will update the parameters of the model, using gradient descent: $$W^{[l]} = W^{[l]} - \alpha \text{ } dW^{[l]} \tag{16}$$ $$b^{[l]} = b^{[l]} - \alpha \text{ } db^{[l]} \tag{17}$$ where $\alpha$ is the learning rate. After computing the updated parameters, store them in the parameters dictionary. Now let's implement update_parameters() to update your parameters using gradient descent. **Tricks**: Update parameters using gradient descent on every $W^{[l]}$ and $b^{[l]}$ for $l = 1, 2, ..., L$. python def update_parameters(parameters, grads, learning_rate): """ Update parameters using gradient descent Arguments: parameters -- python dictionary containing your parameters grads -- python dictionary containing your gradients, output of L_model_backward Returns: parameters -- python dictionary containing your updated parameters parameters["W" + str(l)] = ... parameters["b" + str(l)] = ... """ L = len(parameters) // 2 # number of layers in the neural network # Update rule for each parameter. Use a for loop. for l in range(L): parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - learning_rate * grads["dW" + str(l + 1)] parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - learning_rate * grads["db" + str(l + 1)] return parameters  python parameters, grads = update_parameters_test_case() parameters = update_parameters(parameters, grads, 0.1) print ("W1 = "+ str(parameters["W1"])) print ("b1 = "+ str(parameters["b1"])) print ("W2 = "+ str(parameters["W2"])) print ("b2 = "+ str(parameters["b2"]))  W1 = [[-0.59562069 -0.09991781 -2.14584584 1.82662008] [-1.76569676 -0.80627147 0.51115557 -1.18258802] [-1.0535704 -0.86128581 0.68284052 2.20374577]] b1 = [[-0.04659241] [-1.28888275] [ 0.53405496]] W2 = [[-0.55569196 0.0354055 1.32964895]] b2 = [[-0.84610769]] ## 7 - Conclusion Now we have implemented all the functions required for building a deep neural network! It was a long assignment but going forward it will only get better. In the next Notebook we will put all these together to build two models: - A two-layer neural network - An L-layer neural network We will in fact use these models to classify cat vs non-cat images! *last editted: 31/05/19*
 **Shape of W** **Shape of b** **Activation** **Shape of Activation** **Layer 1** $(n^{[1]},12288)$ $(n^{[1]},1)$ $Z^{[1]} = W^{[1]} X + b^{[1]}$ $(n^{[1]},209)$ **Layer 2** $(n^{[2]}, n^{[1]})$ $(n^{[2]},1)$ $Z^{[2]} = W^{[2]} A^{[1]} + b^{[2]}$ $(n^{[2]}, 209)$ $\vdots$ $\vdots$ $\vdots$ $\vdots$ $\vdots$ **Layer L-1** $(n^{[L-1]}, n^{[L-2]})$ $(n^{[L-1]}, 1)$ $Z^{[L-1]} = W^{[L-1]} A^{[L-2]} + b^{[L-1]}$ $(n^{[L-1]}, 209)$ **Layer L** $(n^{[L]}, n^{[L-1]})$ $(n^{[L]}, 1)$ $Z^{[L]} = W^{[L]} A^{[L-1]} + b^{[L]}$ $(n^{[L]}, 209)$