A vector of size (n,1) is called a row vector.
[[123] [2 4 6] [3 6 9]]
Which of the below formula is used to update weights while performing gradient
descent?
w - learning_rate*dw
For a single neuon network, if number of features is 5, then what would be the
dimension of bias vector?
(5,1) - incorrect
(1,5)
(1,1)
(5,5)
Cost is equal to average of sum of losses.
True
What does it mean if derivatives of parameter with respect to cost is zero?
none of the options
In dot product the number of rows in first matrix must be equal to number of
columns in second.
false
cost function has reached its local minima
0 to 1
What does it mean if derivatives of parameters with respect to cost is negative?
The cost function has reached its minimum!!
current parameter value must be reduced !!
current parameter value must be increased
None of the options
What is the output of print(np.array([1,2,3]) * np.array([1,2,3]) )?
[1 4 9]
Input data is passed through placeholders in TensorFlow?
True
In shallow neural network, number of rows in weight matrix for hidden layer is
equal to number of nodes (neurons) in hidden layer.
True
If a shallow neural network has five hidden neurons with three input features, what
would be the dimension of weight matrix of hidden layer?
(5,5)
(5,3)
(3,5)
(3,3)incorrect
Tensorflows GradientDescentOptimizer() function tries to maximize the cost while
training the network.
false
Hidden layer must use activation function with larger derivative.
True
sigmoid_cross_entropy() function of tensorflow internally performs sigmoid
activation for the final layer output.
True
You are building a binary classifier for classifying output(y=1) vs. output(y=0).
Which one of these activation functions would you recommend using for the output
layer?
sigmoid
If layer_dims = [3,9,9,1], then the shape of weight vector for third layer is
_____________.
(9,9)
If a shallow neural network has five hidden neurons with three input features what
would be the dimension of bias matrix of hidden layer?
(5,3) -incorrect
(5-1) -incorrect
(1,1)
(1,5)
How many hidden layers are present if layer_dims = [3,9,9,1]?
2
For a single neuron network, if number of features is 5 then what would be the
dimension of bias vector?
(1,1)
What is the output range of sigmoid function?
0 to 1
If a shallow neural network has five hidden neurons with three input features what
would be the dimension of weight matrix of hidden layer?
(3,5) -incorrect
In case of DNN weight vector for each layer must always be initialized to zero
before training the network.
True
What is the output of print(np.dot([1,2,3],[[1],[2],[3]])?
[14]
What is the output of print(np.array([1,2,3]) * np.array([[1],[2],[3]]) )?
[[123] [2 4 6] [3 6 9]]
For a single neuon network, if number of features is 5 then what would be the
dimension of weight vector.
(5,1) -incorrect
(1,5) -incorrect
(1,1)
(5,5)
What is the output of print(np.array([1,2,3]) +1)?
[2 3 4]
In a shallow neural network, number of rows in weight matrix for hidden layer is
equal to number of nodes (neurons) in hidden layer.
True
In dot product between two matrix of shape (5,8) and (8,4), what would be the shape
of resultant matrix?
(5,4)
sigmoid_cross_entropy() function of tensorflow internally performs sigmoid
activation for the final layer output.
True
A vector of size (n,1) is called a row vector
true- incorrect
Parameters are initialized as variables in TensorFlow?
true
Hidden layer must use activation function with a larger derivative
true
What does w_2^{[3](1)}w2[3](1) represent according to the notation defined for DNN?
weight with respect to 3rd feature at 2nd node of layer 1-incorrect
weight with respect to 2nd feature at 1st node of layer 3
weight with respect to 3rd feature at 1st node of layer 2
weight with respect to 1st feature at 2nd node of layer 3
Broadcasting in Python throws error when you try to add two vectors of shape(1,5)
and (1,6).
true
