Polished archive of four artificial intelligence and machine learning laboratory assignments. The repository is organized as a compact portfolio project: each lab is isolated, documented, and includes small example inputs for quick local runs.
| Lab | Topic | Main ideas |
|---|---|---|
| 01 Search Algorithms | BFS, UCS, A* | Graph search, path cost, heuristic validation |
| 02 Propositional Logic | Resolution | Clause resolution, proof trace, interactive knowledge base commands |
| 03 Decision Tree ID3 | Classification | Entropy, information gain, tree branches, accuracy, confusion matrix |
| 04 Neural Network + Genetic Algorithm | Optimization | Neural network forward pass, chromosome representation, crossover, mutation |
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txtEach lab can be run independently from its own folder. See the lab-level README files for exact commands and input formats.
- Shows core AI algorithms implemented from scratch in Python.
- Keeps every assignment small, readable, and easy to run.
- Includes examples so reviewers can test behavior without private coursework files.
- Presents the original lab work in a GitHub-friendly structure.
This repository shows algorithmic fundamentals rather than framework use only: graph search, logic resolution, decision trees, neural networks, and genetic optimization are all presented as small runnable exercises with documentation.
labs/
01-search-algorithms/
02-propositional-logic/
03-decision-tree-id3/
04-neural-network-genetic-algorithm/
docs/
input-formats.md
requirements.txt
This is a sanitized portfolio version of a lab archive. Original submission ZIP files, platform-specific folders, and personal submission metadata are not included.