This repository contains various machine learning lab programs that demonstrate foundational algorithms and techniques in machine learning. Each program is designed to help students understand and apply key concepts through practical coding exercises. Below are the programs included in this repository:
-
FIND-S Algorithm
- Implements and demonstrates the FIND-S algorithm to identify the most specific hypothesis from a given set of training data samples. Training data is read from a CSV file, allowing for easy modification and experimentation.
-
Candidate-Elimination Algorithm
- This program implements the Candidate-Elimination algorithm, outputting a description of the set of all hypotheses consistent with the training examples stored in a CSV file. This is useful for understanding how hypotheses can be formed and eliminated based on training data.
-
Decision Tree (ID3 Algorithm)
- Demonstrates the working of the ID3 algorithm for building decision trees. An appropriate dataset is used to train the decision tree, which can then classify new samples, providing insights into classification techniques.
-
Artificial Neural Network (Backpropagation)
- A complete implementation of an Artificial Neural Network using the Backpropagation algorithm. This program tests the network using various datasets, allowing students to observe the learning process and effectiveness of neural networks.
-
Naive Bayesian Classifier
- Implements the Naive Bayesian classifier for a sample training dataset stored as a CSV file. The program calculates the accuracy, precision, and recall of the classifier and can classify a set of documents. It utilizes built-in Java or Python ML library classes for implementation.
-
Heart Disease Diagnosis Model
- This program demonstrates the diagnosis of heart patients using the standard Heart Disease dataset. Implemented with Java or Python ML library classes, this model helps in understanding classification in a medical context.
-
K-Means Clustering
- Applies the K-Means algorithm to cluster a dataset stored in a CSV file. The program utilizes Java or Python ML library classes, offering a practical introduction to clustering techniques.
-
k-Nearest Neighbour Algorithm
- Implements the k-Nearest Neighbour algorithm for classification tasks. The program prints both correct and incorrect predictions, providing insights into the algorithm's performance on various datasets.
-
Locally Weighted Regression
- This program implements the non-parametric Locally Weighted Regression algorithm to fit data points. It selects an appropriate dataset for experimentation and includes graphical representations of the fitted model.
To get started with the programs, clone the repository and follow the individual instructions provided within each program's directory. Each program includes a brief description and usage instructions.
Contributions are welcome! If you have suggestions for improvements or additional algorithms to include, please feel free to fork the repository and submit a pull request.
This repository is licensed under the MIT License.
For any inquiries or feedback, please reach out to me:
- Name: Drona L
- Email: dronanaik1133@gmail.com
- Phone: +91-7022335552