Curriculum Overview
The B.Tech Artificial Intelligence program at Plaksha University Mohali is structured to provide a well-rounded and progressive educational experience. The curriculum spans eight semesters, offering a balance of foundational science subjects, core engineering principles, departmental electives, and hands-on lab work.
First Year
- Calculus I
- Linear Algebra
- Probability & Statistics
- Introduction to Programming (Python)
- Data Structures & Algorithms
- Computer Organization & Architecture
- English for Communication
- Physical Sciences Lab
Second Year
- Discrete Mathematics
- Object-Oriented Programming (Java)
- Database Systems
- Digital Logic Design
- Signals & Systems
- Electronics Devices & Circuits
- Machine Learning Fundamentals
- Programming Lab
Third Year
- Advanced Machine Learning
- Deep Learning
- Computer Vision
- Natural Language Processing
- Reinforcement Learning
- AI Ethics & Governance
- Research Methodology
- Mini Project I
Fourth Year
- Specialized AI Topics (e.g., Generative Models, Explainable AI)
- Capstone Project
- Internship (Optional but Recommended)
- AI Ethics Workshop
- Final Year Thesis
- Professional Development Seminar
Departmental Electives
Students can select from a wide range of departmental electives that align with their interests and career goals:
- Advanced Neural Networks
- Computational Linguistics
- Human-Computer Interaction
- AI in Cybersecurity
- Medical Image Analysis
- Autonomous Systems
- Quantum Machine Learning
- Federated Learning
Science Electives
To ensure a broad scientific foundation, students are encouraged to take science elective courses that complement their technical training:
- Biochemistry
- Psychology of Cognition
- Cognitive Science
- Neuroscience Basics
Labs
Each semester includes lab sessions designed to reinforce theoretical concepts and promote practical application:
- Programming Lab (Python, Java)
- Machine Learning Lab
- Computer Vision Lab
- AI Ethics Lab
- Research Lab
Advanced Departmental Electives
Advanced Neural Networks
This course delves into the design and application of advanced neural architectures such as Transformers, Capsule Networks, and Recurrent Neural Networks (RNNs). Students will implement models for various applications including natural language understanding and image classification.
Computational Linguistics
Focused on building computational systems that can process and generate human language, this course covers topics like syntactic parsing, semantic analysis, and discourse modeling. Students will work with real-world datasets to train and evaluate language models.
Human-Computer Interaction
This course explores how AI can be integrated into interfaces to improve user experience. Topics include user-centered design principles, accessibility, and the ethical implications of AI in human interactions.
AI in Cybersecurity
With cybersecurity threats becoming increasingly sophisticated, this elective teaches students how to leverage AI for detecting anomalies, identifying vulnerabilities, and protecting digital assets. Students will gain hands-on experience with threat detection systems and adversarial machine learning techniques.
Medical Image Analysis
This course applies AI techniques to medical imaging tasks such as segmentation, classification, and diagnosis. Students will work with datasets from hospitals and research institutions to develop models for detecting diseases like cancer and neurological disorders.
Autonomous Systems
Students learn how to design and implement autonomous agents that can navigate complex environments using perception, planning, and control mechanisms. The course includes simulations and real-world robotics projects.
Quantum Machine Learning
This emerging field combines quantum computing with machine learning. Students will explore quantum algorithms for optimization, classification, and regression tasks, preparing them for future developments in hybrid classical-quantum systems.
Federated Learning
As privacy becomes a major concern, federated learning enables training models across distributed devices without sharing data. This course teaches students how to implement secure and efficient distributed AI systems.
Project-Based Learning Philosophy
At Plaksha, we believe that the best way to learn is by doing. Our project-based learning philosophy encourages students to engage with real-world challenges from day one. Projects are designed to be interdisciplinary, requiring students to integrate knowledge from multiple domains.
The mandatory mini-projects begin in the third year and culminate in a final-year thesis or capstone project. These projects allow students to explore specific areas of interest while working closely with faculty mentors. Students are encouraged to present their work at conferences and publish in journals.
Faculty members play a pivotal role in guiding students through the research process, from problem definition to model implementation and evaluation. Each student selects a mentor based on their research interests, ensuring personalized attention and growth opportunities.
The final-year capstone project is a comprehensive endeavor that spans several months. It involves collaboration with industry partners or research institutions, providing students with exposure to real-world challenges and professional environments. The project culminates in a public presentation and submission of a detailed report.