Neural Networks Test 1 β Questions and Answers
Question 1: Which neural network has an entry point into complicated neural nets, where input data goes via several layers of artificial neurons and each node is connected to all neurons in the following layer, resulting in a fully connected neural network?
- Multi-Layer Perceptron (Correct answer)
- Convolutional Neural Network
- Feedforward Neural Networks
- Recurrent Neural Networks
Correct answer: Multi-Layer Perceptron
Explanation: <br> A multilayer perceptron (MLP) is a feedforward artificial neural network that creates outputs from inputs. Multiple layers of input nodes are connected as a directed graph between the input and output layers of an MLP. Multilayer perceptron uses backpropogation to train the network.
Question 2: What distinguishes an automated vehicle?
- Active learning
- Supervised learning (Correct answer)
- Reinforcement learning
- Unsupervised learning
Correct answer: Supervised learning
Explanation: <br> In supervised learning, an educator (for example, a system designer) oversees the artificial neural network and prepares it with labeled data sets using his or her expertise of the system.
Question 3: Choose an application for decision trees in machine learning.
- Classification (Correct answer)
- Unsupervised learning
- Infinite attributes
- Flattening nodes
Correct answer: Classification
Explanation: <br> The act of classifying objects into categories is known as classification. Multiple classes are predicted in this type of classification. Neural units are grouped into layers in neural networks
Question 4: What distinguishes back propagation?
- transmission of errors to adjust weights for the network to learn. (Correct answer)
- A function to determine curve in the perceptron
- The transmission of error back through the network to adjust the inputs
- None of the above
Correct answer: transmission of errors to adjust weights for the network to learn.
Explanation: <br> Neural network training is based on backpropagation. It's a technique for fine-tuning the weights of a neural network using the error rate from the previous epoch (i.e., iteration). By fine-tuning the weights, you may lower error rates and increase the model's generalization, which makes it more dependable.
Question 5: What are the components of a convolutional neural network?
- Pooling
- Local respective fields
- Convolution
- All of the above (Correct answer)
Correct answer: All of the above
Explanation: <br> Convolution, activation, maxpooling, and the fully-connected layer are the fundamental components of a convolutional neural network.
Question 6: What is an activation function that isn't often used?
- ReLU
- Sigmoid
- Tanh
- None of the above (Correct answer)
Correct answer: None of the above
Explanation: <br> The output of a neural network model is determined by activation functions, which are mathematical equations. Activation functions have a significant impact on the ability of neural networks to converge and the pace at which they do so, and in some situations, activation functions may even prevent neural networks from convergent in the first place.
Question 7: A _______ is a decision-making aid that use a tree-like graph or model of decisions and their potential results, such as chance event outcomes, resource costs, and utility.
- Graphs
- Decision tree (Correct answer)
- Neural Networks
- Trees
Correct answer: Decision tree
Explanation: <br> Decision Trees are a supervised non-parametric learning method that may be utilized for both classification and regression applications. The goal is to learn simple decision rules from data attributes to develop a model that predicts the value of a target variable.
Question 8: In machine learning, what does not refer to a neural network layer
- Bias layer (Correct answer)
- Input layer
- Hidden layer
- Neural network layer
Correct answer: Bias layer
Explanation: <br> The addition of a constant value (or a constant vector) to the product of inputs and weights is known as bias. To compensate for the result, bias is used. The bias is used to move the activation function's result to the positive or negative side.
Question 9: Which neural network is fed back into the input to aid in the prediction of the layer's outcome?
- Recurrent Neural Networks (Correct answer)
- Multi-Layer Perceptron
- Convolution Neural Network
- Feedforward Neural Networks
Correct answer: Recurrent Neural Networks
Explanation: <br> The output of the previous step is provided as input to the current step in a recurrent neural network (RNN). All of the inputs and outputs in typical neural networks are independent of one another. However, when predicting the next word of a phrase, the prior words are necessary, and so the previous words must be remembered.
Neural Networks Test 1
Which neural network has an entry point into complicated neural nets, where input data goes via several layers of artificial neurons and each node is connected to all neurons in the following layer, resulting in a fully connected neural network?