Course Syllabus
|
Course Title |
Machine Learning |
||
|
Course Code |
CE717 |
||
|
Course Credits |
Theory :3 |
||
|
Practical :2 |
|||
|
Tutorial :0 |
|||
|
Credits :4 |
|||
|
Course Learning Outcomes: |
|||
|
On the completion of the course, students will be able to:
● Understand the clustering techniques and their utilization in machine learning ● Identify machine learning techniques and the deep learning algorithms which are more appropriate for various types of learning tasks in various domains ● Solve the problems using various machine learning techniques ● Apply Dimensionality reduction techniques ● Design application using machine learning techniques ● Develop intelligent algorithms for constraint satisfaction problems and design intelligent systems ● Implement deep learning algorithms and solve real-world problems ● Formulate and solve problems with uncertain information using Bayesian approaches |
|||
|
Detailed Syllabus |
|||
|
Sr. No. |
Name of chapter and details |
Hours Allotted |
|
|
SECTION-I |
|||
|
1. |
Introduction to Machine Learning Machine learning: What and why? Digital Data – Structured, Unstructured, Semi-Structured Data, what is Machine Learning? Why Machine Learning? Concept of Learning, Types of Machine Learning - Supervised Learning - Unsupervised Learning – Reinforcement Learning. Industrial Applications of Machine Learning Across Domains Such as Healthcare, Finance, Retail etc. The Curse of dimensionality, Overfitting and linear regression, Bias and Variance, Learning Curve, Classification, Error and noise, Parametric vs. non-parametric models-Linear models. |
7 |
|
|
2. |
Unsupervised Learning: Clustering Approaches What is Clustering? Applications of Clustering, Similarity Measures, Partition Based Clustering Techniques – K means Clustering, k-medoid, Hierarchical Clustering, Density Based Clustering, Cluster Validation |
6 |
|
|
3. |
Supervised Learning: Regression, Classification What is Regression? Simple Linear Regression, Multiple Linear Regression, Logistic Regression. What is Classification? Bayesian Classifier, Decision Tree, Issues in decision tree, k-Nearest Neighbour, Support Vector Machine. Classification and regression trees (CART), Random forest, Multivariate adaptive regression trees (MART), Junction tree algorithm. |
8 |
|
|
Total |
21 |
||
|
SECTION-II |
|||
|
4. |
Neural Networks Introduction to Neural Networks, Biological motivation for Neural Network, Neural network Representation, Perceptron. Artificial Neural Network, Feed Forward Neural Network, Multilayer Neural Networks, Activation Function, Loss Function, Learning Rate, Stochastic Gradient Descent |
6 |
|
|
5. |
Training Neural Network: Risk minimization, loss function, backpropagation, regularization, Model selection and Optimization. Conditional Random Fields: Linear chain, Partition function, Markov network, Belief propagation, Training CRFs, Hidden Markov Model, Entropy. |
6 |
|
|
6. |
Deep Learning: Deep Feed Forward network, regularizations, Training Deep Models, Dropouts, Deep Belief Network. Convolutional Neural Networks: Architectures, convolution / pooling layers. Recurrent Neural Networks: LSTM, GRU. Encoder Decoder architectures |
9 |
|
|
7. |
Deep Learning Tools: TensorFlow, Theano, Keras. |
|
|
|
Total |
21 |
||
|
Instructional Method and Pedagogy: |
|||
|
● Lectures will be conducted based on Classroom Response Systems with the use of multimedia projector and black board. ● Assignments based on course contents will be given at the end of each unit/topic and will be evaluated at regular interval. ● Experiments will be based on the practical curriculum and will be evaluated at regular interval. |
|||
|
Reference Books: |
|
● Title: “Machine Learning” by McGraw Hill. Author(s): Tom M Mitchell ● Title: “Introduction to Machine Learning” ● Author(s): E. Alpaydin, MIT Press Edition 2nd Edition, 2009 ● Title: “Neural Network”, Second Edition, Tata-Mc Graw Hill Author(s): E.Rich & K. Knight ● Title: " Artificial Intelligence and Machine Learning", Third Edition, Pearson Education. Author(s): P. H. Winston |
|
Additional Resources |
|
● https://www.coursera.org/learn/machine-learning ● http://course.fast.ai/start.html ● https://www.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6 |