Sie sind auf Seite 1von 2

CP462: MACHINE LEARNING

CREDITS = 5 (L=3, T=0, P=2)

Course objective:
To introduce basic concepts and techniques of machine learning.
Teaching and Assessment Scheme:

Teaching Scheme Credits Assessment Scheme


Total
Theory Practical
L T P C Marks
ESE CE ESE CE
150
3 0 2 5 70 30 30 20

Course Contents:

Unit Teaching
Topics
No. Hours
1 Introduction :
05
Review of Probability theory, Naive Bayesian and Linear Regression,
Overview of Machine Learning and Applications.

2 Linear Models for Classification:


08
Discriminant functions, Probabilistic generative models, Probabilistic
discriminative models, Support Vector Machine (SVM), Applications.

3 Artificial Neural Networks:


10
Introduction, Neural Network representation, Perceptron, Activation
Functions, Feed Forward Network and Recurrent Network, Multilayer
network and back propagation, Learning with momentum, Error
minimization, Applications.

4 Clustering :
10
Unsupervised learning, Clustering methods, Method based on Euclidean
distance, Partitioning, Hierarchical, and Density based approach, Decision
Tree, Method based on probabilities, K – means algorithm, Self-organizing
map.
5 Reinforcement Learning:
04
Introduction, the learning task, Q learning, non-deterministic rewards and
action, Temporal difference learning.

6 Deep Learning:
08
Introduction, Different models, Convolution Neural Network (CNN),
Recurrent Neural Network (RNN), Platforms and software libraries.

TOTAL 45

List of References:
1. Tom Mitchell, “Machine Learning”, McGraw Hill.
2. C. Bishop, “Pattern Recognition and Machine Learning”, Springer.
3. Nils J Nilsson, “Introduction to Machine Learning”, Stanford University.
4. Smola and Vishwanathan, “Introduction to Machine Learning “, Cambridge University
Press.
5. Stuart Russell, Peter Norvig, "Artificial Intelligence: A Modern Approach", Pearson
Education.
Course Outcomes (COs):
After the successful completion of this course the student will be able to
1. Understand the basic concepts of Machine Learning.
2. Compare different learning algorithms.
3. Identify suitability of supervised and unsupervised learning techniques
4. Implement various machine learning techniques.
5. Understand reinforcement learning and deep learning.
6. Develop applications using appropriate machine learning technique.

Das könnte Ihnen auch gefallen