solved questions quizes library in Deep Learning

Assume that your machine has a large enough RAM dedicated to training neural networks. Compared to using stochastic gradient descent for your optimization, choosing a batch size that fits your RAM will lead to::

YasminRadwan26

2022-06-14

1 answers

422 Views

0 Likes

Which of the following methods DOES NOT prevent a model from overfitting to the training set?

YasminRadwan26

2022-06-14

1 answers

522 Views

0 Likes

In which neural net architecture, does weight sharing occur?

YasminRadwan26

2022-06-14

1 answers

498 Views

0 Likes

What consist of Boltzmann machine?

YasminRadwan26

2022-06-14

1 answers

508 Views

0 Likes

Which, if any, of the following propositions is true about fully-connected neural networks (FCNN)?

YasminRadwan26

2022-06-14

1 answers

658 Views

0 Likes

Sentiment analysis using Deep Learning is a many-to one prediction task

YasminRadwan26

2022-06-14

1 answers

788 Views

0 Likes

In CNN, having max pooling always decrease the parameters?

YasminRadwan26

2022-06-14

1 answers

526 Views

0 Likes

Which of the following would have a constant input in each epoch of training a Deep Learning model?

YasminRadwan26

2022-06-14

1 answers

652 Views

0 Likes

In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

YasminRadwan26

2022-06-14

1 answers

552 Views

1 Likes

Assume a simple MLP model with 3 neurons and inputs= 1,2,3. The weights to the input neurons are 4,5 and 6 respectively. Assume the activation function is a linear constant value of 3. What will be the output ?

YasminRadwan26

2022-06-14

1 answers

588 Views

0 Likes

In which of the following applications can we use deep learning to solve the problem?

YasminRadwan26

2022-06-14

1 answers

576 Views

0 Likes

The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are

YasminRadwan26

2022-06-14

1 answers

771 Views

0 Likes

Which of the following functions can be used as an activation function in the output layer if we wish to predict the probabilities of n classes (p1, p2..pk) such that sum of p over all n equals to 1?

YasminRadwan26

2022-06-14

1 answers

531 Views

0 Likes

Deep Learning questions

Deep Learning MCQ Quiz (Multiple Choice Questions And Answers)

Assume that your machine has a large enough RAM dedicated to training neural networks. Compared to using stochastic gradient descent for your optimization, choosing a batch size that fits your RAM will lead to::

Which of the following methods DOES NOT prevent a model from overfitting to the training set?

In which neural net architecture, does weight sharing occur?

What consist of Boltzmann machine?

Which, if any, of the following propositions is true about fully-connected neural networks (FCNN)?

Sentiment analysis using Deep Learning is a many-to one prediction task

In CNN, having max pooling always decrease the parameters?

Which of the following would have a constant input in each epoch of training a Deep Learning model?

In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

Assume a simple MLP model with 3 neurons and inputs= 1,2,3. The weights to the input neurons are 4,5 and 6 respectively. Assume the activation function is a linear constant value of 3. What will be the output ?

In which of the following applications can we use deep learning to solve the problem?

The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are

Which of the following functions can be used as an activation function in the output layer if we wish to predict the probabilities of n classes (p1, p2..pk) such that sum of p over all n equals to 1?