Principles of Deep Learning
This course offers the fundamentals of deep learning technology and its application in real world.
ANNOUNCEMENTS
August 22, 2023: Classes will begin
MTE 2: 24 Nov, 2023
​
EVALUATION COMPONENTS
-
Term tests/quizzes (10%)
-
Assignments + Practical (15%)
-
Class participation (5%)
-
Mid-Term Examination (30%)
-
End Term Examination (40%)
COURSE OBJECTIVES, LEARNING OUTCOMES AND PREREQUISITES
-
To understand the basic concepts of deep learning
-
To use python for solving real world deep learning problems involving classification and regression.
​
Prerequisites: NIL
​
LECTURE NOTES
EXAMINATIONS​
MTE 1: 20 Sep, 2023
MTE 2: 24 Nov, 2023
​
PRACTICE QUIZ
1. Practice Quiz 1: quiz link (click here)
2. Practice Quiz 2: quiz link (click here)
3. Practice Quiz 3: quiz link (click here)
​
ASSIGNMENT
1. Assignment 1: link (click here)
2. Assignment 2:
3. Assignment 3: link (click here)
4. Assignment 4: link (click here) Assigned on- 17 Nov 2023, Deadline- 25 Nov 2023
RECOMMENDED STUDY MATERIAL
​The following will be used as a reference/textbook for this course:
-
Fei Fei Li et al., "CS231n: Deep Learning for Computer Vision", stanford
-
Ian Goodfellow and Yoshua Bengio and Aaron Courville, "Deep Learning", MIT Press, 2016
-
Christopher M. Bishop, "Pattern Recognition and Machine Learning", 2006
-
Tom Mitchell, "Machine Learning", 1997
-
Alpaydin, "Ethem Introduction to Machine Learning", 2014
-
Ian Goodfellow and Yoshua Bengio and Aaron Courville, "Deep Learning", 2016