AI Lab Assignments & Result Reproduction

This repository contains implementations and result reproduction of various Artificial Intelligence (AI) and Machine Learning algorithms as part of academic lab assignments.
The goal of this project is to reproduce results, understand algorithm behavior, and provide both Jupyter Notebook and Python script implementations for learning and experimentation.

---

📂 Repository Structure

The repository includes the following files:

🧠 Jupyter Notebooks (.ipynb)

File Name	Description
AI_Lab2.ipynb	AI Lab 2 experiments and implementations
LabAssignment1.ipynb	AI Lab Assignment 1
A_ResultRep.ipynb	General AI result reproduction
ResultsReproduce.ipynb	Result reproduction for AI algorithms
ResultRepOfKNN.ipynb	K-Nearest Neighbors (KNN) result reproduction
ResultReproduceFuzzy.ipynb	Fuzzy Logic result reproduction
RepBFSDFS.ipynb	BFS and DFS graph traversal result reproduction
RNN_ResultReproduce.ipynb	Recurrent Neural Network (RNN) result reproduction

---

🐍 Python Scripts (.py)

File Name	Description
ai_lab2.py	Python implementation of AI Lab 2
labassignment1.py	Python version of Lab Assignment 1
a_resultrep.py	General AI result reproduction
resultsreproduce.py	Reproducing AI algorithm results
resultrepofknn.py	KNN algorithm result reproduction
resultreproducefuzzy.py	Fuzzy Logic implementation
repbfsdfs.py	BFS and DFS traversal algorithms
rnn_resultreproduce.py	RNN implementation and result reproduction

---

🔍 Algorithms Covered

This repository includes implementations and experiments on:

• Breadth First Search (BFS)
• Depth First Search (DFS)
• K-Nearest Neighbors (KNN)
• Fuzzy Logic Systems
• Recurrent Neural Networks (RNN)
• General AI Lab experiments and assignments

---

⚙️ Requirements

To run the notebooks and scripts, make sure you have:

• Python 3.8+
• Jupyter Notebook / JupyterLab
• NumPy
• Pandas
• Matplotlib
• Scikit-learn
• TensorFlow / Keras (for RNN)

Install dependencies using:

pip install numpy pandas matplotlib scikit-learn tensorflow