TensorFlow Test 1 — Questions and Answers
Question 1: In TensorFlow, which of the following declarations effectively represents an actual neuron?
- A neuron has a single input, however, more than one outputs
- A neuron has a single enter and a single output best
- A neuron has multiple inputs but a single output only
- All of the above (Correct answer)
Correct answer: All of the above
Explanation: <br> All of the above statements are valid
Question 2: In TensorFlow, which of the following procedures is used to cope with overfitting in a neural network?
- Regularization
- Dropout
- Batch Normalization
- All of the above (Correct answer)
Correct answer: All of the above
Explanation: <br> All of the above
Question 3: In TensorFlow, which of the following algorithms performs processes similar to the dropout in a neural community?
- Stacking
- Bagging (Correct answer)
- Boosting
- None of the above
Correct answer: Bagging
Explanation: <br> Bagging is the process of creating many predictors that perform similarly to a single predictor.
Question 4: Batch normalization is useful due to?
- It returns again the normalized mean and widespread deviation of weights
- It miles a very efficient backpropagation method
- It normalizes (adjustments) all the input earlier than sending it to the subsequent layer (Correct answer)
- None of the above
Correct answer: It normalizes (adjustments) all the input earlier than sending it to the subsequent layer
Explanation: <br> When batch normalization is applied to neural networks, the inputs to hidden layers are normalized, resulting in improved outcomes.
Question 5: Which components of convolutional neural networks will conduct classification on the extracted features under Tensorflow?
- Pooling layers
- Dense (fully connected) layers, (Correct answer)
- Convolutional layers
- None of the above
Correct answer: Dense (fully connected) layers,
Explanation: <br> Dense Layer = Fullyconnected Layer = topology, describes how neurons are connected to the next layer of neurons (every neuron in the next layer is connected to every neuron in the next layer), an intermediate layer (also known as hidden layer, see figure) Output Layer = Last layer of a Multilayer Perceptron
Question 6: Which of the following functions should not be used to classify an image at the output layer?
- sigmoid
- tanh
- ReLU (Correct answer)
- None of the above
Correct answer: ReLU
Explanation: <br> The rectified linear activation function (ReLU) is a non-linear or piecewise linear function that outputs the input directly if it is positive and zero otherwise. It is the most often used activation function in neural networks, particularly Convolutional Neural Networks (CNNs) and Multilayer Perceptrons.
Question 7: Under Tensorflow, which components of convolutional neural networks retrieve subregions of the feature map (e.g., 2x2-pixel tiles), maintain their greatest value, and discard all other values?
- Dense (fully connected) layers,
- Convolutional layers
- Pooling layers (Correct answer)
- None of the above
Correct answer: Pooling layers
Explanation: <br> The feature maps' dimensions are reduced by combining layers. As a result, the number of parameters to learn and the quantity of computation done in the network are both reduced. The features contained in a region of the feature map created by a convolution layer are summarized by the pooling layer.
Question 8: A ______ is a network that includes feedback linkages from o/p to i/p as well as hidden layers.
- Recurrent neural network (Correct answer)
- Self organizing maps
- Multi layered perceptron
- All of the above
Correct answer: Recurrent neural network
Explanation: <br> A recurrent neural network (RNN) is a form of artificial neural network that works with time series or sequential data.
Question 9: Under Tensorflow, which components of Convolutional neural networks commonly use a ReLU activation function to the output to incorporate nonlinearities into the model?
- Dense (fully connected) layers,
- Convolutional layers (Correct answer)
- Pooling layers
- None of the above
Correct answer: Convolutional layers
Explanation: <br> The first layer to derive features from the input image is the convolutional layer. By learning visual attributes with a small square of input data, the convolutional layer preserves the link between pixels.
TensorFlow Test 1
In TensorFlow, which of the following declarations effectively represents an actual neuron?