Login
Remember
Register
User rahuljain1
Wall
Recent activity
All questions
All answers
Ask a Question
Questions by rahuljain1
0
votes
0
answers
The chances of arriving at the best set of hyperparameters are high in a random search.
asked
Jan 29, 2020
in
Other
#hyper-parameters-changes
0
votes
0
answers
When you have a large set of hyperparameters, grid search is preferred over a randomized search.
asked
Jan 29, 2020
in
Other
#hyperparameters
0
votes
0
answers
Linear scale search is usually used for choosing many nodes in the layer.
asked
Jan 29, 2020
in
Other
#linear-scale-search
0
votes
0
answers
Batch normalization cannot perform well when there is a change in the distribution of input.
asked
Jan 29, 2020
in
Other
#batch-normalization
0
votes
0
answers
RMS prop reduces the gradients in the vertical direction of gradient steps.
asked
Jan 29, 2020
in
Other
#rms-prop-gradients
0
votes
0
answers
The role of \epsilon? in adam prop is to _______________________.
asked
Jan 29, 2020
in
Other
#numerical-stability
0
votes
0
answers
The gradients in gradient descent with momentum is based on _____________.
asked
Jan 29, 2020
in
Other
#gradient-descent-weight
0
votes
0
answers
Adam prop is the combination of momentum and RMS prop.
asked
Jan 29, 2020
in
Other
#adam-prop-combination
0
votes
0
answers
GD with momentum smooths out the path taken by gradient descent.
asked
Jan 29, 2020
in
Other
#gradient-descent
0
votes
0
answers
GD with momentum reduces the variance of the model.
asked
Jan 29, 2020
in
Other
#gd-momentum-variance
0
votes
1
answer
In GD with momentum, an increase in the value of \betaß increases the time taken for convergence.
asked
Jan 29, 2020
in
Other
#gd-momentum
0
votes
0
answers
RMS prop multiples the root mean square of a gradient with the current gradient.
asked
Jan 29, 2020
in
Other
#rms-prop
0
votes
0
answers
GD with momentum keeps track of gradients calculated from the previous mini batch.
asked
Jan 29, 2020
in
Other
#gd-momentum
+1
vote
1
answer
The formula to calculate the weighted moving average of gradients concerning weights is _______________.
asked
Jan 28, 2020
in
Data Handling
DataHandling-questions-answers
0
votes
1
answer
Hidden layer must use activation function with a larger derivative.
asked
Jan 28, 2020
in
Data Handling
#hidden-layer
DataHandling-questions-answers
0
votes
1
answer
What is the output of print(np.array([1,2,3]) * np.array([[1],[2],[3]]) )?
asked
Jan 28, 2020
in
Data Handling
#print-output
DataHandling-questions-answers
+1
vote
1
answer
What is the output of print(np.dot([1,2,3],[[1],[2],[3]])?
asked
Jan 28, 2020
in
Data Handling
#output-print
DataHandling-questions-answers
+1
vote
1
answer
Tensorflows GradientDescentOptimizer() function tries to maximize the cost while training the network.
asked
Jan 28, 2020
in
Data Handling
#gradientdescentoptimizer
DataHandling-questions-answers
+1
vote
1
answer
If a shallow neural network has five hidden neurons with three input features what would be the dimension of bias matrix of hidden layer?
asked
Jan 28, 2020
in
Data Handling
#shallow-neural-network
DataHandling-questions-answers
0
votes
1
answer
Parameters are initialized as variables in TensorFlow.
asked
Jan 28, 2020
in
Data Handling
#parameter-initialization
DataHandling-questions-answers
0
votes
1
answer
In shallow neural network, number of rows in weight matrix for hidden layer is equal to number of nodes (neurons) in hidden layer.
asked
Jan 28, 2020
in
Data Handling
#shallow-neural
DataHandling-questions-answers
+1
vote
1
answer
Input data is passed through placeholders in TensorFlow.
asked
Jan 28, 2020
in
Data Handling
#tensorflow
DataHandling-questions-answers
+1
vote
1
answer
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?
asked
Jan 28, 2020
in
Data Handling
#binary-classifier
DataHandling-questions-answers
0
votes
1
answer
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)?
asked
Jan 28, 2020
in
Data Handling
#linear-output
DataHandling-questions-answers
+1
vote
1
answer
What is the output of print(np.array([1,2,3]) * np.array([1,2,3]) )?
asked
Jan 28, 2020
in
Data Handling
#output-array
DataHandling-questions-answers
+1
vote
1
answer
If layer_dims = [3,9,9,1], then the shape of weight vector for third layer is _____________.
asked
Jan 28, 2020
in
Data Handling
#vector-weight
DataHandling-questions-answers
0
votes
1
answer
sigmoid_cross_entropy() function of tensorflow internally performs sigmoid activation for the final layer output.
asked
Jan 28, 2020
in
Data Handling
sigmoid-cross-entropy
#tensorflow
DataHandling-questions-answers
0
votes
1
answer
A vector of size (n,1) is called a row vector.
asked
Jan 28, 2020
in
Data Handling
#vector-size
DataHandling-questions-answers
+1
vote
1
answer
In dot product the number of rows in first matrix must be equal to number of columns in second.
asked
Jan 28, 2020
in
Data Handling
#dot-product
DataHandling-questions-answers
+1
vote
1
answer
What does it mean if derivatives of parameters with respect to cost is negative?
asked
Jan 28, 2020
in
Data Handling
#derivatives-parameters
DataHandling-questions-answers
Page:
« prev
1
...
53
54
55
56
57
58
59
60
61
62
63
...
69
next »
...
