MACHINE LEARNING

MACHINE LEARNING Syllabus (15CS73)

MACHINE LEARNING Syllabus (15CS73)

Subject Code: 15CS73                     Semester: 7              Scheme: CBCS

Text Books:

1. Tom M. Mitchell, Machine Learning, India Edition 2013, McGraw Hill Education

Reference Books:

1. Trevor Hastie, Robert Tibshirani, Jerome Friedman, h The Elements of Statistical Learning, 2nd edition, springer series in statistics.
2. Ethem Alpaydın, Introduction to machine learning, second edition, MIT press.

Module – 1: Text Book1, Sections: 1.1 – 1.3, 2.1-2.5, 2.7

• Introduction: 
• Well posed learning problems
• Designing a Learning system
• Perspective and Issues in Machine Learning.
• Concept Learning: 
• Concept learning task 
• Concept learning as search 
• Find-S algorithm 
• Version space
• Candidate Elimination algorithm 
• Inductive Bias

Module – 2: Text Book1, Sections: 3.1-3.7

• Decision Tree Learning: 
• Decision tree representation
• Appropriate problems for decision tree learning
• Basic decision tree learning algorithm
• hypothesis space search in decision tree learning 
• Inductive bias in decision tree learning
• Issues in decision tree learning

Module – 3: Text book 1, Sections: 4.1 – 4.6

• Artificial Neural Networks: 
• Introduction
• Neural Network representation
• Appropriate problems
• Perceptrons
• Backpropagation algorithm

Module – 4: Text book 1, Sections: 6.1 – 6.6, 6.9, 6.11, 6.12

• Bayesian Learning: 
• Introduction
• Bayes theorem 
• Bayes theorem and concept learning
• ML and LS error hypothesis
• ML for predicting probabilities
• MDL principle
• Naive Bayes classifier
• Bayesian belief networks
• EM algorithm

Module – 5: Text book 1, Sections: 5.1-5.6, 8.1-8.5, 13.1-13.3

• Evaluating Hypothesis: 
• Motivation
• Estimating hypothesis accuracy
• Basics of sampling theorem
• General approach for deriving confidence intervals
• Difference in error of two hypothesis
• Comparing learning algorithms
• Instance Based Learning: 
• Introduction
• k-nearest neighbor learning
• locally weighted regression 
• radial basis function cased-based reasoning
• Reinforcement Learning: 
• Introduction
• Learning Task 
• Q Learning

MACHINE LEARNING LABORATORY (15CSL76)

MACHINE LEARNING LABORATORY

NOTE:

1. The programs can be implemented in either JAVA or Python.
2. For Problems 1 to 6 and 10, programs are to be developed without using the built-in 

    classes  or APIs of Java/Python.
3. Data sets can be taken from standard repositories 

    (https://archive.ics.uci.edu/ml/datasets.html) or constructed by the students.

1. Implement and demonstrate the FIND-S algorithm for finding the most specific hypothesis  based on a given set of training data samples. Read the training data from a .CSV file.
2. For a given set of training data examples stored in a .CSV file, implement and 
    demonstrate the Candidate-Elimination algorithm to output a description of the set 
    
   of all hypotheses consistent with the training examples.
3. Write a program to demonstrate the working of the decision tree based ID3 algorithm. Use an appropriate data set for building the decision tree and apply this knowledge to classify a new  sample.
4. Build an Artificial Neural Network by implementing the Backpropagation algorithm and test the same using appropriate data sets.
5. Write a program to implement the naïve Bayesian classifier for a sample training 
    data set stored as a .CSV file. Compute the accuracy of the classifier, considering few 
    
   test data sets.
6. Assuming a set of documents that need to be classified, use the naïve Bayesian 
    Classifier model to perform this task. Built-in Java classes/API can be used to write 
    
   the program. Calculate the accuracy, precision, and recall for your data set. 
7. Write a program to construct a Bayesian network considering medical data. Use this 
    

   model to demonstrate the diagnosis of heart patients using standard Heart Disease 

    
   Data Set. You can use Java/Python ML library classes/API. 
8. Apply EM algorithm to cluster a set of data stored in a .CSV file. Use the same data 
    set for clustering using k-Means algorithm. Compare the results of these two 
    
   algorithms and comment on the quality of clustering. You can add Java/Python ML 
    
   library classes/API in the program.
9. Write a program to implement k-Nearest Neighbour algorithm to classify the iris 
    

   data set. Print both correct and wrong predictions. Java/Python ML library classes can 

    
   be used for this  problem.
10. Implement the non-parametric Locally Weighted Regression algorithm in order to 
     fit data  points. Select appropriate data set for your experiment and draw graphs.

https://tejaswinihbhat.blogspot.com/2018/07/machine-learning-15CSL76-program9-KNN.html