Artificial Intelligence — What This Subject Is About
A thermostat senses the room temperature and switches the heater on. A chess program looks ahead through thousands of moves and picks the best one. A washing machine decides how dirty the clothes are and adjusts the wash. All three are doing something we call intelligence — and this subject teaches you how machines do it. Artificial Intelligence at the diploma level is about the fundamentals: what an intelligent agent is, how a machine searches for a solution, how fuzzy logic handles answers that are not simply yes or no, and how a neural network learns from examples.
The subject has only three units: an introduction to AI; agents, environments and search; and fuzzy logic systems and neural networks. It is a qualifying Open Elective-III subject: you must pass it, but its 50 internal marks are not counted in your percentage or division, and there is no external paper. The syllabus prints no unit-wise periods or marks distribution, so no weightage is claimed anywhere on this page.
One thing students get wrong from the start: AI is not magic and it is not a robot with a face. In this syllabus AI is three concrete ideas — an agent that perceives and acts, a search that finds a path to a goal, and a network that learns from examples. Learn those three and the whole subject falls into place.
Subject 5.6.3 (Open Elective-III, Qualifying) • 50 Marks Internal Only • 2 Credits • L 2 – P 0 • 5th Semester — Mechanical Engineering (Production) • Session 2026–27

What You Will Study
Unit 1 — Introduction to Artificial Intelligence
Artificial Intelligence (AI) definition; goals of AI; history of AI; applications of AI.
What AI means, what it is trying to achieve, how it developed, and where it is used — speech recognition, vision processing, problem-solving and autonomous control.
Unit 2 — Agents, Environments & Algorithms Terminology
Agent terminology; types of agents (simple reflex agents, model based reflex agents, goal based agents); nature of environments; properties of environments. Brute force search strategies: breadth first search, depth first search. Heuristic search strategies; local search algorithms.
The biggest unit: what an agent is, the three agent types in order of capability, the environments they work in, and the search strategies — brute force, heuristic and local — that find a path to a goal.
Unit 3 — Fuzzy Logic Systems & Neural Networks
Introduction to fuzzy logic and fuzzy systems; membership functions; fuzzification/defuzzification. Basic structure of neural networks; perceptron; back-propagation.
How machines handle answers that are not simply yes or no (fuzzy logic), and how a network of simple units learns from examples — the perceptron and back-propagation.
Complete Syllabus
The full examination scheme and the reference books from the official syllabus. The unit-wise topics are in the “What You Will Study” section above. The syllabus prints no unit-wise periods and no marks-distribution table for this subject.
Examination Scheme
| Code | Paper | Type | L – P | Credits | Internal | External | Total |
|---|---|---|---|---|---|---|---|
| 5.6.3 | Artificial Intelligence | Qualifying | 2 – 0 | 2 | 50 | — | 50† |
Units at a Glance
| Unit | Topic |
|---|---|
| 1 | Introduction to Artificial Intelligence |
| 2 | Agents, Environments & Algorithms Terminology |
| 3 | Fuzzy Logic Systems & Neural Networks |
Reference Books
As listed in the syllabus:
- Artificial Intelligence By Example: Develop machine intelligence from scratch using real artificial intelligence use cases — Denis Rothman, Packt Publishing, ISBN 978-1788990547.
- Artificial Intelligence by E. Balagurusamy.
- Artificial Intelligence: A Simplified Approach by Sinha, P. Royston.
- Introduction to Artificial Intelligence by Dan W. Patterson.
How to Prepare for Artificial Intelligence
Learn the two worked examples by hand. They are the only numbers in the subject: the breadth-first and depth-first search orders on a small tree (BFS visits level by level, DFS goes deep first), and the perceptron firing test (weighted sum against a threshold). Both are in the notes — work them yourself, do not just read them.
Learn the three agent types in order of capability. Simple reflex, model based reflex, goal based — each one can do what the previous one cannot, and the exam loves asking what each type adds.
Give Unit 2 the most time. It is the biggest unit: agents, environments and all four search strategies. Learn BFS vs DFS as a pair, and heuristic search as the practical method.
Keep one example for every Unit 3 idea. A fuzzy set (hot water), a membership function (how hot is hot), a perceptron (firing or not) — one concrete example each makes the abstract ideas answerable.
Finish with timed practice. Work through the practice sets in one sitting of 2.30 hours, without notes — the suggested practice time. Then compare your answers with the model answer outline and note the points you missed.
Exam Tips
- Remember it is qualifying. There is no external paper — your 50 marks come from internal assessment. Take the internal tests and assignments seriously; a fail here still means a fail, even though the marks do not count towards your division.
- Attempt all five questions in the practice paper. The pattern gives three parts (a), (b) and (c) in each question, of which any two are to be answered — pick the two parts you know best in every question, and do not leave any question blank.
- Work the tree, do not memorise it. In a BFS/DFS question, draw the tree and walk it: level by level for BFS, deep first for DFS. The order follows from the walk.
- Show the perceptron arithmetic. Write the weighted sum, the threshold and the comparison — the marks are in the working, not just the answer.
- Do not invent weightage. The syllabus prints no unit-wise marks distribution — prepare all three units, and give Unit 2 the most time because it is the biggest, not because any marks split says so.
Frequently Asked Questions
Is Artificial Intelligence a qualifying subject?
Yes. It is an Open Elective-III subject, assessed internally for 50 marks only, with no external examination. You must pass it, but its marks are not added to your awarded division or total marks.
Which Open Elective-III options can I choose instead?
You choose ONE option: Computer Aided Design & Manufacturing, Reverse Engineering, Artificial Intelligence, Automobile Engineering, or any minimum-2-credit course (NPTEL/SWAYAM/AICTE-ELIS/C-DAC/IIT-NIT/ISRO/Tata Tech). The four taught options are linked in the Related Posts section below.
Is this the same as the Electronics AI & Machine Learning subject?
No. The Mechanical 5th-semester Artificial Intelligence elective has 3 units and is conceptual — no programming language is prescribed. The Electronics 5th-semester AI & Machine Learning subject has 7 sections including machine learning and programming. They are different subjects with different syllabi.
How many units are there in this subject?
Three units in the official syllabus: Introduction to AI, Agents/Environments/Search, and Fuzzy Logic/Neural Networks. The notes split them into five study units so the practice paper follows the board's five-question pattern — nothing is added and nothing is dropped.
Does the syllabus give a unit-wise marks distribution?
No. The official syllabus prints no unit-wise periods and no marks-distribution table for this subject, so no weightage is claimed on this page or in the notes.
How can I download the syllabus PDF?
The PDF is free to download — use the download links in the Download section below (English and Hindi versions). It is prepared by KAMALDNP from the official BTEUP syllabus.
Related Syllabus Posts
- Computer Aided Design & Manufacturing — BTEUP Mechanical 5th Semester Syllabus 2026-27
- Reverse Engineering — BTEUP Mechanical 5th Semester Syllabus 2026-27
- Automobile Engineering — BTEUP Mechanical 5th Semester Syllabus 2026-27
- Indian Constitution — BTEUP Mechanical 5th Semester Syllabus 2026-27
- All BTEUP Syllabus Posts — kamaldnp.com Blog
Notes, Question Bank & Practice Sets — Artificial Intelligence
The syllabus PDF on this page stays 100% FREE — no login, no payment, always. The study material below is a paid KAMALDNP product: buy once for just ₹10 and you get both the Hindi and English PDFs. Every PDF is generated with your name and enrolment number and is password-locked, so it remains personal to you. After purchase, the PDF is also sent to your email, and it is always available for download on the My Downloads page.
Unit-wise short revision notes prepared from the official BTEUP 2026-27 syllabus of this subject.
Buy / Download — My DownloadsOne original practice (model) paper with a model-answer outline. This is a KAMALDNP practice paper — NOT a BTEUP board paper, and no question in it is promised to appear in your exam.
Buy / Download — My Downloads10 Practice Sets — practice/guess sets only (no verified previous-year board papers available for this subject yet)
Buy / Download — My DownloadsAlready purchased? You will find the Download button on the same My Downloads page — you will not be charged again.
Download the Artificial Intelligence Syllabus PDF
Download the complete Artificial Intelligence syllabus PDF below — prepared by KAMALDNP, with the full topic list, examination scheme and reference books.
Download the Artificial Intelligence Syllabus PDF (English)
Source: BTEUP IRDT Kanpur NEP-2020 curriculum for Diploma in Mechanical Engineering (Production), effective session 2026-27, approved by the Board of Technical Education U.P. Lucknow in the C.D.C. meeting held on 16.07.2026 (urise.up.gov.in). Topic lists follow the official syllabus; short explanations are the author's own plain-English summaries, not syllabus text. Please confirm with your own polytechnic for any local changes.
Comments (0)
Share your question or experience about this syllabus. Your comment will appear after review.
No comments yet — be the first to share your thoughts!