A comprehensive academic resource for Artificial Intelligence and Soft Computing (AISC) and AISC Laboratory, covering search strategies, knowledge representation, neural networks, fuzzy logic, and genetic algorithms.
Overview · Contents · Reference Books · Assignments · Quizzes · Laboratory · Case Study · Internal Assessment Test · Semester Exam · Question Papers · Submission Report · Syllabus · Usage Guidelines · License · About · Acknowledgments
Artificial Intelligence and Soft Computing (CSC703) and AISC Lab (CSL703) are core subjects in the Final Year (Semester VII) of the Computer Engineering curriculum at the University of Mumbai. Those courses provide foundational knowledge of intelligent systems, logic programming, and soft computing paradigms.
The curriculum encompasses several key domains in Artificial Intelligence and Soft Computing (AISC):
- Intelligent Agents: Agents and environments, rational agents, PEAS representation.
- Problem Solving: Uninformed search (BFS, DFS, IDDFS), Informed search (A*, Heuristic functions).
- Knowledge Representation: First-order logic, interference, Forward and Backward chaining.
- Uncertainty: Probabilistic reasoning, Bayesian networks.
- Soft Computing: Neural Networks (Perceptron, Backpropagation), Fuzzy Logic, Genetic Algorithms.
- Expert Systems: Architecture and applications.
This repository represents a curated collection of study materials, reference books, lab experiments, and personal preparation notes compiled during my academic journey. The primary motivation for creating and maintaining this archive is simple yet profound: to preserve knowledge for continuous learning and future reference.
As a computer engineer, understanding AI and soft computing is crucial for developing modern intelligent applications. This repository serves as my intellectual reference point: a resource I can return to for relearning concepts, reviewing methodologies, and strengthening understanding when needed.
Why this repository exists:
- Knowledge Preservation: To maintain organized access to comprehensive study materials beyond the classroom.
- Continuous Learning: To support lifelong learning by enabling easy revisitation of fundamental concepts.
- Academic Documentation: To authentically document my learning journey through AISC.
- Community Contribution: To share these resources with students and learners who may benefit from them.
All materials in this repository were gathered, organized, and documented by me during my undergraduate studies (2018-2022) as part of my coursework and exam preparation.
This collection includes comprehensive reference materials covering all major topics:
| # | Resource | Focus Area |
|---|---|---|
| 1 | AI: A Modern Approach (3rd Ed) | The standard textbook for Artificial Intelligence |
| 2 | AISC Toppers Solution | Solved exams and top-scoring answers |
| 3 | AISC Module 1 | Introduction to AI and Intelligent Agents |
| 4 | AISC Module 2 | Problem Solving and Search Strategies |
| 5 | AISC Module 3 | Knowledge Representation and Logic |
| 6 | AISC Module 4 | AI Planning and Uncertainty |
| 7 | AISC Module 5 | Artificial Neural Networks |
| 8 | AISC Module 6 | Fuzzy Logic and Expert Systems |
| 9 | Expert Systems Notes | Dedicated notes on Expert Systems |
| 10 | Planning Notes | Dedicated notes on Planning in AI |
| 11 | Uncertainty Notes | Dedicated notes on Uncertainty |
| 12 | AISC Index | Index of topics and notes |
Academic assignments for comprehensive learning and practice:
| # | Assignment | Description | Date | Marks |
|---|---|---|---|---|
| 1 | Assignment 1 | Intelligent Agents, PEAS, A* Algorithm, Resolution Logic | October 22, 2021 | 10/10 |
| 2 | Assignment 2 | Fuzzy Logic, Perceptron Learning rule, EBPTA, ANFIS, Genetic Algorithm steps | October 22, 2021 | 10/10 |
| 3 | Assignment 3 | AI Tools and Libraries (Detailed description and architecture) | October 22, 2021 | 10/10 |
Topics Covered: Fundamentals of AI · Intelligent Agents · Search Algorithms · Logic Programming · Fuzzy Logic · Neural Networks · Genetic Algorithms · AI Tools
AISC-specific quizzes conducted during the course:
| # | Quiz | Topics | Marks |
|---|---|---|---|
| 1 | Quiz 1 | Introduction to AI | 10/10 |
| 2 | Quiz 2 | Search Strategies | 10/10 |
| 3 | Quiz 3 | Knowledge Representation | 9/10 |
| 4 | Quiz 4 | Planning and Uncertainty | 10/10 |
| 5 | Quiz 5 | Artificial Neural Networks | 10/10 |
| 6 | Quiz 6 | Fuzzy Logic and Expert Systems | 10/10 |
The laboratory component (CSL703) focuses on hands-on implementation of AI algorithms including Search strategies, PROLOG programming, and Soft Computing techniques like Neural Networks and Fuzzy Logic.
Tip
Prerequisites: This laboratory requires a versatile development setup. Ensure you have SWI-Prolog installed for logic programming (Experiment 2), a C/C++ Compiler for search algorithms (Experiments 3-4), and MATLAB/Python (with NumPy) for neural networks and fuzzy logic simulations.
| # | Experiment | Date | Marks | Report |
|---|---|---|---|---|
| 1 | Identify a problem statement relevant to AI and describe its PEAS Descriptors with its Properties | July 27, 2021 | 9/10 | View |
| 2 | A case study on Basic Programming in PROLOG and Develop a program to implement a family tree | August 03, 2021 | 10/10 | View |
| 3 | To Implement uninformed search methods using C or Java | August 10, 2021 | 9/10 | View |
| 4 | To Implement informed A* search methods using C or Java | August 20, 2021 | 9/10 | View |
| 5 | Identify the Classification problem and create a Knowledge database for that problem and apply appropriate search methods for optimization | August 24, 2021 | 10/10 | View |
| 6 | To implement a program to calculate cartesian product on fuzzy relation using 1. Max-Min and 2. Max-Product composition | September 21, 2021 | 8/10 | View |
| 7 | To Implement Fuzzy-Controller | October 02, 2021 | 9/10 | View |
| 8 | To implement McCulloch Pitts Neuron Model for AND/OR functions | October 05, 2021 | 9/10 | View |
| 9 | To Implement Kohonen self-organizing Map- un-supervised learning algorithm | October 06, 2021 | 9/10 | View |
| 10 | Case Study: Neuro-Fuzzy - Artificial Neural Networks & Fuzzy Logic | October 22, 2021 | 9/10 | View |
Experiment 2: Family Tree (PROLOG)
| Program | Category | Description | Code |
|---|---|---|---|
Family_Tree_Abstract.pl |
Logic Programming | Knowledge base for basic family relationships (Abstract) | View |
Family_Tree_Concrete.pl |
Logic Programming | Knowledge base for extended family relationships (Concrete) | View |
Experiment 3: Uninformed Search (C)
| Program | Category | Description | Code |
|---|---|---|---|
Uninformed_Search_BFS.c |
Search Strategy | Implementation of Breadth-First Search (BFS) | View |
Uninformed_Search_DFS.c |
Search Strategy | Implementation of Depth-First Search (DFS) | View |
Experiment 4: Informed Search (Python)
| Program | Category | Description | Code |
|---|---|---|---|
Informed_Search_AStar.py |
Python Programming | Implementation of A* Algorithm | View |
Experiment 5: Flower Classification (Weka)
| Resource | Category | Description | Link |
|---|---|---|---|
Flowers.arff |
Weka Dataset | Flower Classification Database | View |
Model |
Analysis | Learned Models | View |
Output |
Results | Classification Accuracy Results | View |
Experiment 6: Fuzzy Relations (C)
| Program | Category | Description | Code |
|---|---|---|---|
Fuzzy_Relations_Composition.c |
Soft Computing | Fuzzy Relations Composition (Max-Min & Max-Product) | View |
Experiment 7: Fuzzy Controller (MATLAB)
| Program | Category | Description | Code |
|---|---|---|---|
Fuzzy_Controller.m.txt |
Soft Computing | Fuzzy Logic Controller Implementation | View |
Experiment 8: McCulloch Pitts Neuron (Python)
| Program | Category | Description | Code |
|---|---|---|---|
McCulloch_Pitts_Neuron.py |
Neural Networks | McCulloch Pitts Neuron Model for AND/OR | View |
McCulloch_Pitts_Neuron.ipynb |
Neural Networks | Interactive Notebook | View |
Experiment 9: Kohonen SOM (MATLAB)
| Program | Category | Description | Code |
|---|---|---|---|
Kohonen_SOM.m.txt |
Neural Networks | Kohonen Self-Organizing Map Implementation | View |
Experiment 10: Case Study (Neuro-Fuzzy)
| Document | Category | Description | Link |
|---|---|---|---|
AMEY_B-50_AI_SC_EXPERIMENT-10.pdf |
Report | Individual Experiment Report | View |
AISC_EXPERIMENT_10_B-28_B-31_B-50.pdf |
Case Study | Group Case Study Report | View |
AISC_EXPERIMENT_10_PPT.pdf |
Presentation | Case Study Presentation | View |
Neuro-Fuzzy_Artificial Neural Networks_&_Fuzzy Logic.pdf |
Reference | Topic Reference Material | View |
| # | Resource | Description |
|---|---|---|
| 1 | Lab README | Detailed navigation guide with program descriptions |
Design and Implementation of a Neuro-Fuzzy System using Artificial Neural Networks and Fuzzy Logic
Important
Special thanks to Karan Dhiman for his meaningful contributions, guidance, and support that helped shape this work.
A hybrid Neuro-Fuzzy system developed as a case study for the Artificial Intelligence and Soft Computing Lab. This system integrates the learning capabilities of Artificial Neural Networks with the reasoning power of Fuzzy Logic to create a robust model for pattern recognition and decision making. By combining these paradigms, the project demonstrates how to handle complex, non-linear data processing tasks effectively.
Note
Research Impact: This project was published as a research paper in International Journal for Research in Applied Science & Engineering Technology (IJRASET) (Volume 9, Issue IX) and is also available as a preprint on viXra.
| # | Resource | Description | Date | Marks | Link |
|---|---|---|---|---|---|
| 1 | Case Study Report | Detailed documentation and system design | October 22, 2021 | 09/10 | View |
| 2 | Presentation | Visual overview of the development lifecycle | October 22, 2021 | 09/10 | View |
| 3 | Research Paper | Neuro-Fuzzy: Artificial Neural Networks & Fuzzy Logic | September 6, 2021 | - | View |
| 4 | ResearchGate | Research paper available on ResearchGate | September 2021 | - | View |
Internal assessment evaluations conducted during the course:
| # | Resource | Description |
|---|---|---|
| 1 | Answer Sheet | AISC Internal Assessment Test 1 Answer Sheet |
| # | Resource | Description |
|---|---|---|
| 1 | Answer Sheet | AISC Internal Assessment Test 2 Answer Sheet |
Important
COVID-19 Impact: This coursework was completed during the COVID-19 pandemic. All examinations and assessments were conducted in a digital format.
Final semester examination submission:
| # | Resource | Description | Date |
|---|---|---|---|
| 1 | Answer Sheet | AISC Semester Exam Answer Sheet | November 26, 2021 |
University of Mumbai examination papers from 2012-2019:
| # | Exam Session | Syllabus | Resource |
|---|---|---|---|
| 1 | May 2019 | CBCGS | View |
| 2 | December 2018 | CBCGS | View |
| 3 | May 2018 | CBCGS | View |
| 4 | December 2017 | CBCGS | View |
| 5 | May 2017 | CBCGS | View |
| 6 | December 2016 | CBCGS | View |
| 7 | May 2016 | CBCGS | View |
| 8 | December 2015 | CBGS | View |
| 9 | May 2015 | CBGS | View |
| 10 | December 2014 | CBGS | View |
| 11 | May 2014 | CBGS | View |
| 12 | December 2013 | CBGS | View |
| 13 | May 2013 | CBGS | View |
| 14 | December 2012 | CBGS | View |
| 15 | May 2012 | CBGS | View |
Course completion documentation with exit survey:
| # | Document | Description |
|---|---|---|
| 1 | Submission Report | Final coursework submission report |
| 2 | Exit Survey (Lab) | Course outcome survey for AISC Laboratory |
Official CBCGS Syllabus
Complete Final Year Computer Engineering syllabus document from the University of Mumbai, including detailed course outcomes, assessment criteria, and module specifications for AISC and AISC Lab.
Important
Always verify the latest syllabus details with the official University of Mumbai website, as curriculum updates may occur after this repository's archival date.
This repository is openly shared to support learning and knowledge exchange across the academic community.
For Students
Use these resources as reference materials for understanding AI algorithms, soft computing models, and preparing for examinations. All content is organized for self-paced learning.
For Educators
These materials may serve as curriculum references, lab examples, or supplementary teaching resources. Attribution is appreciated when utilizing content.
For Researchers
The documentation and organization may provide insights into academic resource curation and educational content structuring.
This repository and all linked academic content are made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0). See the LICENSE file for complete terms.
Note
Summary: You are free to share and adapt this content for any purpose, even commercially, as long as you provide appropriate attribution to the original author.
Created & Maintained by: Amey Thakur
Academic Journey: Bachelor of Engineering in Computer Engineering (2018-2022)
Institution: Terna Engineering College, Navi Mumbai
University: University of Mumbai
This repository represents a comprehensive collection of study materials, reference books, assignments, and personal preparation notes curated during my academic journey. All content has been carefully organized and documented to serve as a valuable resource for students pursuing Artificial Intelligence and Soft Computing and Artificial Intelligence and Soft Computing Laboratory.
Grateful acknowledgment to Karan Dhiman for his exceptional support and collaboration during the development of the Hybrid Neuro-Fuzzy System mini project for this course. Working alongside him was a truly enriching experience - his technical expertise in artificial neural networks, dedication to exploring soft computing paradigms, and enthusiasm for innovation turned every challenge into a meaningful learning opportunity. Our shared curiosity and collaborative efforts in integrating neural networks with fuzzy logic were essential to the project's success. Thank you, Karan, for being such an outstanding project partner and for all the knowledge and encouragement you shared along the way.
Grateful acknowledgment to the faculty members of the Department of Computer Engineering at Terna Engineering College for their guidance and instruction in Artificial Intelligence and Soft Computing. Their clear teaching and continued support helped develop a strong understanding of intelligent systems and soft computing paradigms.
Special thanks to the mentors and peers whose encouragement, discussions, and support contributed meaningfully to this learning experience.
Overview · Contents · Reference Books · Assignments · Quizzes · Laboratory · Case Study · Internal Assessment Test · Semester Exam · Question Papers · Submission Report · Syllabus · Usage Guidelines · License · About · Acknowledgments
Computer Engineering (B.E.) - University of Mumbai
Semester-wise curriculum, laboratories, projects, and academic notes.