{ .tiet-logo }

UTA027: Artificial Intelligence
TIET Patiala

Course Website

Instructors:

1. ( RGB) Raghav B. Venkataramaiyer <bv.raghav>
2. ( STT) Stuti Chug <stuti.chug>
3. ( ABJ) Anu Bajaj <anu.bajaj>
4. (PTKRA) Parteek Saini <psaini_phd24>

~^(1)^~Academic Calendar :material-file-pdf-box:

1. Requires thapar.edu login

<iframe src="https://calendar.google.com/calendar/embed?height=600&wkst=1&ctz=Asia%2FKolkata&mode=AGENDA&src=Y18wNDFiZjNjZGU2MTc2OGNjYTQzMTFlNDZhNDdiNGExNTZiM2JhMjIzNTZkYTRhMjU3NGNhMDhlNDI5OGNjZTI5QGdyb3VwLmNhbGVuZGFyLmdvb2dsZS5jb20&src=Y181MWMwYmJjZmRiMWVkYTI4ZDIzYzIwNDUxYjA4ZDM1ZjVhMDA0M2UzYzgxOTFlMzZkOTY0YzA5Mzc3MWQyNGZmQGdyb3VwLmNhbGVuZGFyLmdvb2dsZS5jb20&src=Y180YWU5NGJkYmJkNWM5YjY1NzNjNjljMmMxNTdlNTU1NzFiMmZiNWUyOTc0MTEwMTE0Y2EwOGEyMGY0ZWVlNTg3QGdyb3VwLmNhbGVuZGFyLmdvb2dsZS5jb20&src=Y18wZjhmMWI1OWFiOGI2YzdhN2NmMzg4YTRhZTRjYWE1NmQyYWFlYzBiODJhMjVhNjVlYTRkM2VhMWVjNjZhODU4QGdyb3VwLmNhbGVuZGFyLmdvb2dsZS5jb20&color=%23795548&color=%23D81B60&color=%233F51B5&color=%23C0CA33" style="border:solid 1px #777" width="800" height="600" frameborder="0" scrolling="no"></iframe>

Course Syllabus :material-file-pdf-box:

Download :material-file-pdf-box:

Evaluation

Code	Title	Date	Weightage
SESS#A1	Assignment 1	CE	10
SESS#A2	Assignment 2	CE	10
SESS#QZ1	Quiz 1	18-02-2025 1730 IST	05
MST	Mid Sem Exam	TBA	25
SESS#QZ2	Quiz 2	06-05-2025 1730 IST	05
EST	End Sem	TBA	45

Schedule of Lectures

Orientation

1. :simple-googleslides: Overview{: target="_blank" } and administrative details.

Predicate Calculus [MST]  [EST]{: .htag }

1. :simple-googleslides: Predicate Calculus{: target="_blank" }
   Introduction to Predicate Logic and Representation of Knowledge and Heuristics
2. :simple-googleslides: Reasoning{: target="_blank" } (Predicate Calculus)
3. Application to Knowledge Graphs and Lifecycle of a research problem

See also: A01{: target="_blank" }

The Graphical Standpoint [MST]  [EST]{: .htag }

1. :simple-googleslides: Graph Theory{: target="_blank" } + :simple-googleslides: BFS/DFS{: target="_blank" }.
2. :simple-googleslides: Dijkstra’s Algorithm{: target="_blank" } for Single-Source Shortest Path.
3. :simple-googleslides: Problem solving from a graphical stand point{: target="_blank" }

Classical ML [MST]  [EST]{: .htag }

1. :simple-googleslides: Introduction to ML{: target="_blank" }
2. :simple-googleslides: Linear Regression{: target="_blank" }
3. :simple-googleslides: Classification and Logistic Regression{: target="_blank" }
4. :simple-googleslides: Support Vector Machines{: target="_blank" }

See Also: ML Notes or, Download :material-file-pdf-box:

Neural Methods [MST]  [EST]{: .htag }

1. :simple-googleslides: Neuron and it application in Regression/ Classification{: target="_blank" }
2. :simple-googleslides: Deep Neural Networks{: target="_blank" }
3. Deep Learning: Residuals, Gating and RNN’s
4. State Machines and Reinforcement Learning

Computer Vision [EST]{: .htag }

1. :simple-googleslides: Computer Vision Overview
2. :simple-googleslides: Computer Vision Problems
3. Deep Learning in Computer Vision: :simple-googleslides: Lecture Set 1{: target="_blank" }, Lecture Set 2.

Introduction to Advanced Topics [EST]{: .htag }

1. Attention
2. Diffusion
3. Inverse Rendering

Schedule of Assignments¹²³

S.No.	Desc/Link	Deadline
A01	Predicate Calculus{: target="_blank" }	20-01-2025 0500 IST
A02	Graph Methods (TBA) Practice: Python and Algos	10-02-2025 0500 IST
A03	Linear Regression	24-02-2025 0500 IST
A04	Neuron-based Regression	24-Mar to 4-Apr
A05	Neural Regression (Iris Dataset)	7-Apr to 18-Apr
A06	Visual Object Classification	21-Apr to 2-May
A07	YOLO	4-May to 15-May
A08	Visual Object Detection	21-04-2025 0500 IST
A09	GAN based Generative AI	28-04-2025 0500 IST
A10	Proposals	05-05-2025 0500 IST

Resources

1. [CL]{: .htag } The Central Library (Link)
2. [RR]{: .htag } RefRead (Link)
3. [TB]{: .htag} [CL]{: .htag } [RR]{: .htag } Luger, G. F. & others. (1998). Artificial intelligence: Structures and strategies for complex problem solving (Sixth). Pearson Education India. ISBN: 9788131743744
4. [TB]{: .htag} [CL]{: .htag } Bishop, C. M. (2006). Pattern recognition and machine learning. Springer. ISBN: 9788132209065
5. [RB]{: .htag} [CL]{: .htag } Cormen, T. H., Leiserson, C. E., Rivest, R. L., & Stein, C. (2022). Introduction to Algorithms (Fourth). MIT Press. ISBN: 9788120340077
6. [RB]{: .htag} [CL]{: .htag } Gareth James, Daniela Witten, Trevor Hastie, & Robert Tibshirani. (2013). An Introduction to Statistical Learning (1st ed.). Springer. DOI: 10.1007/978-1-4614-7138-7 ISBN: 9781461471387 (Link)
7. [RB]{: .htag } [CL]{: .htag } MacKay, D. J. C. (2003). Information theory, inference and learning algorithms. Cambridge University Press. ISBN: 9780521670517 (Link)
8. [RB]{: .htag } Bertsekas, D., & Tsitsiklis, J. N. (2008). Introduction to probability (Vol. 1). Athena Scientific. ISBN: 9781886529236 (Google Scholar)
9. [YT]{: .htag } [MOOC]{: .htag } Introduction to Probability. (MIT-OCW) (Archive 2011) (Archive 2018)
10. [YT]{: .htag } [MOOC]{: .htag } Algorithms Illuminated. by Tim Roughgarden Videos: Part 1 Basics, Videos: Part 2 Graphs and Official Website
11. [RB]{: .htag } [CL]{: .htag } Jurafsky, D., & Martin, J. H. (2025, January). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. ISBN: 9789332518414 (The Book), (The Chapter on Logistic Regression), (Official Website)
12. [MOOC]{: .htag } Illinois Institute Page on Logistic Regression.
13. [YT]{: .htag } Late Prof. Winston’s Lecture on SVM (MIT-OCW) Video by MIT-OCW

*[CE]: Continuous Evaluation

*[TB]: Text Book

*[RB]: Reference Book

*[CL]: Accessible through the Central Library.

*[RR]: RefRead subscription accessible through TIET.

*[YT]: Youtube Video/Playlist

*[MOOC]: Online Course (or a part of it)

Footnotes

1. Each assignment carries weightage of 2 marks ↩

2. Some of the assignments are competition and leaderboard based; Marks awarded shall be based on rank on leaderboard. ↩

3. A01-05 A01-03 shall reflect on the webkiosk as consolidated SESS#A1 (MM:10); and similary A06-10 A04-07 as SESS#A2 (MM:10). ↩