Course Title Deep Learning Course Type Theory
Course Code B22EKS506 Credits 3 Class VI semester
Contact Work Total Number of
TLP Credits Assessment in
Hours
Classes Weightage
Theory 3 3 3 Per Semester
Course
Structure Practice - - -
Theor
Tutorial - - - Practical CIE SEE
y
Total 3 3 3 42 0 50% 50%
COURSE OVERVIEW:
Course Description: This course is an introduction to deep learning, a branch of machine learning concerned with the
development and application of modern neural networks. Deep learning algorithms extract layered high-level representations
of data in a way that maximizes performance on a given task. Deep learning is behind many recent advances in AI, including
Siri’s speech recognition, Facebook’s tag suggestions and self-driving cars.
COURSE OBJECTIVE:
The objectives of this course are to:
1. Explain the basic concepts of Deep Learning.
2. Describe supervised and unsupervised learning.
3. Demonstrate the use of a deep learning neural network in a real world application.
4. Illustrate the use of deep learning techniques in neural networks and natural language processing
COURSE OUTCOMES (COs)
After the completion of the course, the student will be able to:
CO# Course Outcomes POs PSOs
Apply the basic concepts of mathematics to solve problems based on deep 1,2,3,4 1,2
CO1
learning concepts.
Make use of suitable machine learning algorithms on real world problems 1,3,4,5,8 1,2
CO2 (classification, clustering).
CO3 Utilize deep learning neural network model on real time applications. 1,3,4,5,8 1,3
CO4 Develop Recommender systems applications using CNN concepts of NLP. 1,2,4,5 1
Learn new tools and technologies in the deep learning and apply for 12 1,2
CO5 suitable application development
Develop solutions in the deep learning to the complex problems, either 5,9,10 1,2
CO6 individually or as a part of the team and report the results with proper
analysis and interpretation.
BLOOM’S LEVELOF THECOURSE OUTCOMES
Bloom’s Level
CO# Remember Understand Apply Analyze Evaluate Create
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √ √
CO2 √
CO3 √
CO4 √
CO5 √ √
CO6 √ √
COURSE ARTICULATION MATRIX
PO10
PO11
PO12
PSO1
PSO2
PSO3
PO1
PO2
PO3
PO4
PO5
PO6
PO7
PO8
PO9
CO#/ POs
CO1 2 2 1 2 3 3
CO2 2 1 2 1 1 3 3
CO3 1 1 2 2 1 3 3
CO4 1 1 2 1 3
CO5 2 2
CO6 2 2 2 2 2
Note: 1-Low,2-Medium,3-High
COURSE CONTENT
THEORY:
Contents
UNIT-1
Machine Learning Basics: Linear Algebra-Scalars, Vectors, Matrices and Tensors, Eigen Decomposition, SVD, PCA
Probability and Information Theory-Probability Distribution, Conditional Probability, Chain Rule of Conditional Probability,
Bayes’ Rule.
UNIT-2
Numerical Computation: Overflow, Underflow, Gradient Based Optimization, Constrained Optimization, Linear Least
Squares, Machine Learning Basics- Learning Algorithms, Overfitting and Under fitting, Maximum Likelihood Estimation,
Supervised and Unsupervised Learning Algorithms, Building Machine Learning Algorithm, Challenges Motivating Deep
Learning.
UNIT-3
Deep Networks: Modern Practices-Example: Learning XOR, Gradient-Based Learning, Hidden Units, Architectural Design,
Back-Propagation Algorithm.
UNIT-4
Convolutional Networks: Recurrent Neural Networks, Applications- Natural Language Processing, Recommender
Systems.
TEXT BOOKS:
1. Bengio, Yoshua, Ian J. Good fellow, and Aaron Courville. "Deep learning." First edition, An
MIT Press book in preparation, 2015.
REFERENCE BOOKS:
1. Duda, R.O., Hart, P.E., and Stork, D.G. “Pattern Classification”, Wiley-Interscience. 2nd Edition. 2001.
2. Theodoridis, S. and Koutroumbas, K. ,”Pattern Recognition”, Edition 4. Academic Press, 2008.
3. Russell, S. and Norvig, N. ,”Artificial Intelligence: A Modern Approach”, Prentice Hall Series in Artificial
Intelligence. 2003.
JOURNALS/MAGAZINES
1. Springer Journal of Machine Learning, https://www.springer.com/journal/10994
2. http://ieeexplore.ieee.org/document/8297269/
SWAYAM/NPTEL/MOOCs:
1. https://www.my-mooc.com/en/categorie/deep-learning
2. https://nptel.ac.in/courses/106/105/106105215/
SELF-LEARNING EXERCISES:
Linear factor Models, Structured probabilistic Models, Monte-Carlo Methods, and Deep generative
Moodles.
