Welcome to my repository of deep learning projects! This space serves as a portfolio of my work and a log of my progress in the field of Artificial Intelligence. Each project here represents a new concept learned and a new problem solved.
Here is a summary of the projects completed so far. As I continue to learn, this list will grow.
| # | Project Name | Description | Key Concepts Learned |
|---|---|---|---|
| 1 | Handwritten Digit Recognition (MNIST) | A foundational "Hello, World!" project for image classification. This notebook builds a simple feed-forward neural network to recognize handwritten digits from 0 to 9 with ~98% accuracy. | TensorFlow/Keras, Sequential Model, Dense Layers, Data Preprocessing & Normalization, Model Training & Evaluation |
| 2 | IMDb Movie Review Sentiment Analysis | An introductory NLP project performing binary classification on movie reviews. The model uses word embeddings and dense layers with Dropout regularization to fix overfitting, achieving ~87.8% accuracy. | NLP & Word Embeddings, Sequence Padding, Binary Classification, Dropout Regularization, GlobalAveragePooling1D, Overfitting Analysis |
- Primary Framework: TensorFlow & Keras
- Core Libraries: NumPy, Matplotlib
- Development Environment: Kaggle Notebooks
- Version Control: Git & GitHub
Each project is contained within its own Jupyter Notebook (.ipynb file). To explore a project, you can clone this repository and run the notebook in an environment like Kaggle, Google Colab, or a local setup with the required libraries installed.