B.Tech in Machine Learning – Semester-wise Syllabus 

 

Year 1: Foundations of Computing & Mathematics 

Semester 1:

1. Mathematics-I: Linear Algebra, Calculus 

2. Programming Fundamentals: Python Basics, Control Structures 

3. Physics for Engineers / Computational Thinking

4. Digital Logic & Computer Organization 

5. Introduction to Machine Learning: Basic Concepts, Applications 

6. Lab: Python Programming, Simple ML Models (Regression, Classification) 

 

Semester 2: 

1. Mathematics-II: Probability, Statistics 

2. Data Structures & Algorithms: Arrays, Trees, Graphs, Sorting 

3. Discrete Mathematics: Logic, Sets, Combinatorics 

4. Object-Oriented Programming (C++/Java) 

5. Database Management Systems: SQL, NoSQL Basics 

6. Lab: Data Structures Projects, SQL Queries 

 

Year 2: Core Machine Learning & Data Science

Semester 3: 

1. Statistics for ML: Distributions, Hypothesis Testing, Bayesian Inference 

2. Supervised Learning: Linear/Logistic Regression, Decision Trees, SVMs 

3. Data Preprocessing & Visualization: Pandas, Matplotlib, Seaborn 

4. Operating Systems: Processes, Memory Management 

5. Optimization Techniques: Gradient Descent, Convex Optimization 

6. Lab: Scikit-learn Projects, EDA (Exploratory Data Analysis) 

 

Semester 4: 

1. Unsupervised Learning: Clustering (K-Means, DBSCAN), PCA, Dimensionality Reduction 

2. Deep Learning Basics: Neural Networks, Backpropagation 

3. Reinforcement Learning: Markov Decision Processes, Q-Learning 

4. Big Data Technologies: Hadoop, Spark Basics 

5. Software Engineering: Agile, Version Control (Git) 

6. Lab: TensorFlow/Keras Projects, Spark Data Processing 

 

Year 3: Advanced ML & Domain Applications 

Semester 5: 

1. Natural Language Processing (NLP): Tokenization, Transformers, BERT 

2. Computer Vision: CNN, Object Detection, OpenCV 

3. Time Series Analysis: ARIMA, LSTM Networks 

4. Elective-I: Healthcare Analytics / FinTech / Robotics 

5. Cloud Computing: AWS/Azure ML Services 

6. Lab: NLP Pipelines, Image Classification (PyTorch) 

 

Semester 6: 

1. Advanced Deep Learning: GANs, Autoencoders, Transfer Learning 

2. MLOps: Model Deployment, Docker, CI/CD Pipelines 

3. AI Ethics & Fairness: Bias Mitigation, Explainable AI (XAI) 

4. Elective-II: Autonomous Systems / Recommender Systems 

5. Elective-III: Quantum Machine Learning / Edge AI 

6. Lab: Deploying Models (Flask/Django), Ethical AI Case Studies 

 

Year 4: Specialization & Industry Integration 

Semester 7: 

1. Advanced Topics in ML: Federated Learning, Meta-Learning 

2. Domain-Specific ML: Genomics, IoT, Cybersecurity 

3. Elective-IV: Generative AI / AI for Sustainability 

4. Elective-V: Advanced Robotics / AI in Gaming 

5. Capstone Project-I: Industry/Research Problem (e.g., Predictive Maintenance, Fraud Detection) 

6. Internship: AI Labs (Google, NVIDIA), Startups, or Research Institutes 

 

Semester 8: 

1. Project Management: Scrum, Data Governance 

2. Entrepreneurship in AI: Startups, IP Rights 

3. Emerging Trends: AI Legislation, Neuromorphic Computing 

4. Capstone Project-II: End-to-End ML Solution Development 

5. Seminar/Technical Paper Presentation 

 

Electives (Sample Options): 

- Healthcare: Medical Imaging, Drug Discovery 

- Finance: Algorithmic Trading, Risk Modeling 

- Robotics: SLAM, Reinforcement Learning for Control 

- NLP: Multilingual Models, Voice Assistants 

- Sustainability: Climate Modeling, Energy Optimization 

- Creative AI: Art Generation, Music Synthesis 

 

Key Tools & Labs: 

- Programming: Python, R, Julia 

- Frameworks: TensorFlow, PyTorch, Hugging Face, LangChain 

- Cloud Platforms: AWS SageMaker, Google Colab, Azure ML 

- Visualization: Tableau, Power BI 

- Big Data: Apache Spark, Kafka 

- Deployment: Docker, Kubernetes, Flask