This repository showcases projects and implementations from my Master's degree, with a focus on Deep Learning concepts and a fundamental, from-scratch neural network implementation.
DeepLearning/
This directory holds all files related to the Deep Learning course completed during my Master's program. Here, you'll find assignments, project code, and relevant resources explored throughout the course.
DeepLearningWithTensorFlow
This directory contains implementations and materials related to the DeepLearning With TensorFlow short course from Udemy.
HandsOnMachineLearning
This directory contains implementations resulting from the study of the book:
- "Hands-On: Machine Learning with Scikit-Learning, Keras, and TensorFlow" by Aurélien Géron (2019)
MakeYourOwnNeuralNetwork/
This directory features a neural network implementation built from scratch, meaning it doesn't rely on high-level frameworks like TensorFlow, Keras, or PyTorch. This foundational implementation is based on the principles outlined in one key resource:
- "Make Your Own Neural Network" by Tariq Rashid (2016)
This section offers a deep dive into the core mechanics of neural networks, providing a clear understanding of their underlying operations.
To access and explore the code, simply clone this repository to your local machine:
git clone git@github.com:thiagoneye/master-deep_learning.gitOnce cloned, navigate into the respective directories (DeepLearning/, DeepLearningWithTensorFlow, HandsOnMachineLearning, or MakeYourOwnNeuralNetwork/) to find the code and any specific instructions or dependencies within their individual README files.
While specific technologies and libraries may vary slightly by project, the primary tools and libraries generally include:
- Python
- NumPy: Essential for numerical operations, especially in the
MakeYourOwnNeuralNetwork/section. - Pandas: For data manipulation and analysis.
- Matplotlib: For data visualization.
- Scikit-Learn: For preprocessing and evaluation metrics.