Course Structure

The Computer Science curriculum at Girijananda Chowdhury University Kamrup is meticulously structured over eight semesters to ensure a progressive and comprehensive learning experience. Each semester builds upon the previous one, integrating theoretical knowledge with practical applications.

Advanced Departmental Electives

Deep Learning: This course introduces students to deep neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers. Students learn to build and train models for image classification, natural language processing, and generative modeling using frameworks like TensorFlow and PyTorch.

Natural Language Processing: This elective explores text processing techniques, sentiment analysis, named entity recognition, machine translation, and chatbots. Students gain hands-on experience with tools like spaCy, NLTK, and Hugging Face Transformers while working on projects involving real-world datasets.

Computer Vision: The course covers image processing, object detection, segmentation, and feature extraction using computer vision libraries such as OpenCV and TensorFlow. Students implement algorithms for facial recognition, autonomous vehicles, and medical imaging applications.

Data Mining and Warehousing: This subject teaches students how to extract patterns from large datasets using clustering, classification, association rules, and anomaly detection techniques. Practical sessions involve working with tools like Weka, KNIME, and Apache Spark.

Cloud Computing: Students learn about virtualization, distributed computing models, cloud services (IaaS, PaaS, SaaS), and platform-specific technologies like AWS, Azure, and Google Cloud Platform. Projects include deploying applications on cloud infrastructure and managing scalability issues.

Big Data Technologies: This course introduces Hadoop ecosystem components including HDFS, MapReduce, YARN, and Hive. Students gain expertise in processing large volumes of data using Spark SQL, streaming APIs, and real-time analytics platforms.

Quantum Computing Fundamentals: An introductory look into quantum mechanics and quantum algorithms. Students study qubit manipulation, superposition, entanglement, and error correction. Hands-on sessions involve simulating quantum circuits using Qiskit and Cirq frameworks.

Game Development: Focuses on game design principles, 3D modeling, scripting, physics engines, and rendering techniques. Students create interactive games using Unity or Unreal Engine, integrating sound, graphics, and user interfaces.

Reinforcement Learning: This elective covers Markov Decision Processes (MDPs), Q-learning, policy gradients, actor-critic methods, and exploration-exploitation trade-offs. Students implement reinforcement learning agents in simulated environments and real-world applications.

Software Testing and Quality Assurance: Covers manual testing strategies, automated testing tools, test case design, and quality metrics. Students learn to apply continuous integration practices and ensure software reliability through comprehensive testing methodologies.

Mobile Application Development: Involves building cross-platform mobile apps using frameworks like React Native or Flutter. Topics include UI/UX design, API integration, offline functionality, and app deployment on various platforms.

Cryptography and Network Security: Introduces symmetric and asymmetric encryption, hash functions, digital signatures, secure protocols (SSL/TLS), and network security threats. Students implement cryptographic algorithms and conduct penetration testing exercises.

Artificial Intelligence Ethics: Examines ethical implications of AI technologies in society, including bias in machine learning models, privacy concerns, algorithmic transparency, and regulatory compliance. Students analyze real-world cases and propose mitigation strategies.

Human-Computer Interaction: Focuses on usability evaluation methods, user experience design principles, prototyping techniques, and accessibility standards. Projects involve conducting user research, designing interfaces, and testing prototypes with target audiences.

Project-Based Learning Philosophy

Our department strongly believes in project-based learning as a means to reinforce theoretical concepts and develop practical skills. Mini-projects are integrated into the curriculum from the second year onwards, allowing students to apply classroom knowledge to real-world scenarios.

Each mini-project is designed around a specific theme or challenge that aligns with industry trends. Students work in teams under faculty supervision, learning collaborative problem-solving techniques and project management skills. These projects often evolve into capstone initiatives in the final year.

The final-year thesis/capstone project provides students with an opportunity to explore advanced topics within their area of interest. They select a mentor from among faculty members based on shared research interests or project relevance. The process involves proposal development, literature review, implementation, experimentation, and documentation.

Students are encouraged to present their work at conferences or publish papers in journals. We provide guidance on writing technical reports, preparing presentations, and defending ideas before expert panels. This approach ensures that graduates not only understand concepts but can also communicate them effectively to diverse audiences.