Machine Learning2 - UNIT 2 : Decision Tree and Artificial Neural Network Questions

UNIT-2 
Short Answer Questions 
  •  Define Entropy and Information Gain. 
  •  What is the purpose of Entropy and Information Gain in ID3. 
  •  Define Overfitting. 
  •  Define Decision Tree. 
  •  Define Perceptron. 
  •  Define neural networks 
  •  What is backpropagation 
  •  Define Neuron. 
Long Answer Questions 
  •  Appropriate Problems for Decision Tree Learning. 
  •  Construct the decision tree for the following dataset. 


  •  What is the entropy of this collection of training examples with respect to the target function classification? 
  •  What is the information gain of a_2 relative to these training examples. 
  •  Draw the decision tree for the given dataset. 
  •  List the different issues in Decision Tree Learning. Explain. 
  •  Define Overfitting. How to overfitting data in decision tree construction? 
  •  How can you incorporate the continuous values? Explain. 
  •  Give decision trees to represent the following Boolean functions: 
 A ∧¬ B 
 A ∨ [B ∧ C] 
 A XOR B 
 [A∧ B] ∨ [C ∧ D] 
  •  Define Entropy and Information Gain in ID3 with an example? 
  •  Explain ID3 algorithm. 
  •  What is Artificial Neural Network? What are the type of problems in which Artificial Neural Network can be applied. 
  •  Explain the concept of a Perceptron with a neat diagram. 
  •  Discuss the Perceptron training rule. 
  •  Under what conditions the perceptron rule fails and it becomes necessary to apply the delta rule What do you mean by Gradient Descent? 
  •  Derive the Gradient Descent Rule. 
  •  What are the conditions in which Gradient Descent is applied. What are the difficulties in applying Gradient Descent. 
  •  Differentiate between Gradient Descent and Stochastic Gradient Descent Define Delta Rule. 
  •  Derive the Backpropagation rule considering the training rule for Output Unit weights and Training Rule for Hidden Unit weights Write the algorithm for Back propagation. 
  •  Explain how to learn Multilayer Networks using Gradient Descent Algorithm.
  •  What is Squashing Function? 
  •  How a multi layered network learns using a gradient descent algorithm? 
  • Discuss Discuss in detail about representation of Neural Networks Explain back-propagation algorithm in detail. 
  •  Explain the Back propagation learning algorithm and its limitations. 
  •  Discuss the issues related to neural network learning Construct decision tree for the following dataset using ID3.



Comments

Post a Comment