DeepLearning Lab Summer2023 FAT MCQ

A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2. The inputs are 4, 3, 2 and 1 respectively. What will be the output?

• 30

• 40

• 50

• 60

What is back propagation?

• It is another name given to the curvy function in the perceptron

• It is the transmission of error back through the network to adjust the inputs

• It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn

• None of the mentioned

After receiving the outcome, it is compared with the original one, and the weights are updated is referred to as ____________?

• Feed forward network

• Artificial Neural Network

• Backpropagation

• CNN

What is back propagation?

• 
  it is another name given to the curvy function in the perceptron

• it is the transmission of error back through the network to adjust the inputs

• 
  it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

• None of the mentioned

What is the meaning of generalized in statement “backpropagation is a generalized delta rule” ?

• Because delta is applied to only input and output layers, thus making it more simple and generalized

• Because delta rule can be extended to hidden layer units

• It has no significance

• None of the mentioned

________ computes the output volume by computing dot product between all filters and input image. 

• Input Layer

• Convolution Layer

• Activation Function Layer

• Pool Layer

If the input image is a 300 X 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5x5. How many parameters does this hidden layer have (without bias)

• 2501

• 1500

• 7500

• 7600

If the input image is a 300 X 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5x5. What will the dimension of the resulting activation function?

• 300X300X100

• 250X250X250

• 296X296X100

• 300X300X300

What is the basic concept of Recurrent Neural Network?

• Use previous inputs to find the next output according to the training set.

• Use loops between the most important features to predict next output.

• Use a loop between inputs and outputs in order to achieve the better prediction.

• Use recurrent features from dataset to find the best answers.

To which of these tasks would you apply a many-to-one RNN architecture?

• Speech recognition (input an audio clip and output a transcript)

• Sentiment classification (input a piece of text and output a 0/1 to denote positive or negative sentiment)

• Text translation

• Text summarization