This repository contains Jupyter notebooks documenting my introduction to machine learning, with a specific focus on Artificial Neural Networks (ANNs).
Through these projects, I explored fundamental machine learning concepts, including:
- Data Preprocessing
- Model Building
- Training and Evaluation
- Visualization of Results
I used PyTorch as the primary framework for building and training neural networks, providing a strong foundation in understanding how ANNs function.
In this notebook, I developed an ANN to classify two distinct types of Qwerties. The process involved:
- Preprocessing the data
- Designing the neural network architecture with PyTorch
- Training the model
- Evaluating its performance
- Visualizing the results using various performance metrics
This project helped me understand the basics of single-output classification and how to tune models for better accuracy.
This notebook introduced me to multi-output classification for Qwerties. The steps included:
- Generating and preprocessing the necessary data
- Designing and training a robust ANN model using PyTorch
- Evaluating and visualizing the model’s performance
This project deepened my understanding of advanced classification techniques and how to interpret model results in a multi-output context.
Building on the Qwerties project, this notebook focused on multi-output classification tasks for different species of flowers. The process involved:
- Importing and processing the dataset
- Creating a more complex ANN capable of handling multiple outputs
- Training the model
- Analyzing and visualizing the model’s predictions
This project allowed me to grasp the intricacies of multi-label classification and how to effectively handle such datasets.
This project provided hands-on experience in machine learning and neural networks. I learned how to build, train, and evaluate ANN models for single-output and multi-output classification tasks.