This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Neurons and the Brain”.
1. Which of the following statements is not true about neural networks?
a) They are class of very powerful machine learning classifiers
b) Neural networks are a class of computationally inexpensive algorithms
c) These are capable of fitting almost any hypotheses
d) NN has lots of interconnected nodes which are organized in layers
View Answer
Explanation: Neural Network (NN) is a very powerful and widely used model to learn a complex non-linear hypothesis for many applications. They are class of very powerful machine learning classifiers. NN are a class of computationally expensive algorithms that are capable of fitting almost any hypotheses. And it has lots of interconnected nodes which are organized in layers.
2. Which of the following statements is not true about the given figure?
a) We can treat a node as an Activation Function, which can output a computation value based on activation function
b) The terminology of parameters W in NN is called weights
c) Bias unit is mandatory in neural networks
d) The input values can be the input features
View Answer
Explanation: Given figure represents a simplest neural network. A neural network is composed of neurons, which are very simple elements that take in a numeric input (features), apply an activation function to it and pass it as the output. Depending on the problems, you can decide whether to use the bias units or not. So bias is not a mandatory thing in NN.
3. Which of the following statements is not true about the structure of a neural network?
a) It consists of a set of nodes connected by links
b) Not every link in a neural network is associated with a weight
c) The processing elements in the neural network are known as neurons
d) A set of thresholds or activation is used
View Answer
Explanation: The processing elements in the NN are known as neurons and the connection between the neurons as links. So, the structure of a neural network consists of a set of nodes connected by links and every link is associated with a weight. Also, a set of thresholds or activation is used in a NN.
4. The initialization and training of the weights on the interconnections through the training set require in the design of a neural network.
a) True
b) False
View Answer
Explanation: While designing a neural network, the initialization and training of the weights on the interconnections through the training set is important. Also, the choice of number and type of units, the determination of the morphological structure (layers), and coding of training examples in terms of inputs and outputs from the network is also essential.
Sanfoundry Global Education & Learning Series – Neural Networks.
To practice all areas of Neural Networks, here is complete set on 1000+ Multiple Choice Questions and Answers.
