Neural Networks and Deep Learning Quiz Question and Answers
In shallow neural network, number of rows in weight matrix for hidden layer is equal to number of nodes (neurons) in hidden layer.
- True
- False
In dot product the number of rows in first matrix must be equal to number of columns in second.
- True
- False
Cost is equal to average of sum of losses.
- True
- False
Hidden layer must use activation function with a larger derivative.
- True
- False
A vector of size (n,1) is called a row vector.
- True
- False
Broadcasting in Python throws error when you try to add two vectors of shape(1,5) and (1,6).
- True
- False
In case of DNN weight vector for each layer must always be initialized to zero before training the network.
- True
- False
Which of the below formula is used to update weights while performing gradient descent?
- dw – learning_rate*w
- w – learning_rate*dw
- w /learning_rate*dw
- w +learning_rate*dw
What does it mean if derivatives of parameters with respect to cost is negative?
- Current parameter value must be reduced
- The cost function has reached its minimum
- Current parameter value must be increased
- None of the options
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?
- tanh
- relu
- sigmoid
- leaky-relu
What is the equation for linear output of a hidden_layer in shallow neural network, if X is of shape (num_features, num_samples) and W is of shape(num_neurons, num_input)?
- Z = W.X+b
- Z = transpose(W).X +b
- Z = W.transpose(X) + b
- Z = X.W + b
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)
- (5,1)
- (1,1)
- (1,5)
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)
- (3,3)
- (5,3)
- (3,5)
For a single neuron network, if number of features is 5 then what would be the dimension of bias vector?
- (5,5)
- (1,1)
- (1,5)
- (5,1)
What is the output of print(np.array([1,2,3]) * np.array([1,2,3]) )?
- [14]
- [1 4 9]
- [1 2 3 1 2 3]
- [14 14 14]
What is the output of print(np.dot([1,2,3],[[1],[2],[3]])?
- [[1 2 3] [2 4 6] [3 6 9]]
- throws error
- [14]
- [[14]]
What is the output of print(np.array([1,2,3]) +1)?
- [11 21 31]
- [1 1 2 3]
- [1 2 3 1]
- [2 3 4]
If layer_dims = [3,9,9,1], then the shape of weight vector for third layer is _____________.
- (9,3)
- (9,1)
- (9,9)
- (3,9)
How many hidden layers are present if layer_dims = [3,9,9,1]?
- 1
- 2
- 3
- 4
If layer_dims = [3,9,9,1], then the shape of weight vector for third layer is _____________.
- (9,3)
- (5,5)
- (5,3)
- (3,5)
View More Quiz Questions and Answer
👉MFDM AI Quiz