Deep learning has become a cornerstone of modern data science, enabling powerful solutions in areas such as computer vision, natural language processing, and time series forecasting. This repository documents my structured learning journey through the Udemy course “PyTorch for Deep Learning with Python Bootcamp.”
PyTorch is a widely used open-source deep learning framework that provides a seamless path from research prototyping to production deployment. Its deep integration with Python and dynamic computational graph makes it especially suitable for building, training, and experimenting with neural network models.
This repository combines theoretical understanding with hands-on Jupyter notebook implementations. It will progressively include practical exercises, model implementations, and experiments covering core deep learning architectures such as Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN).
The primary objective of this repository is to develop a solid end-to-end understanding of deep learning workflows using PyTorch and to build reproducible implementations that can be extended to real-world analytical and forecasting problems.
Anaconda / Python / Jupyter Notebook
Sample datasets used in the exercises are available in the Data folder of the repository. Each dataset corresponds to the examples provided in the notebooks.
This file provides basic instructions and codes to create a new environment, activate/deactivate an environment, and install relevant packages.
This notebook provides a hands-on introduction to NumPy, the foundational library for numerical computing in Python. It focuses on building and manipulating arrays, performing vectorized operations, and understanding core functionalities that support deep learning workflows.
The notebook includes practical examples covering:
- Creation of NumPy arrays
- Array indexing and slicing
- Mathematical and element-wise operations
- Broadcasting concepts
- Random number generation
This chapter establishes the numerical computing foundation required for subsequent deep learning implementations in PyTorch.
This notebook introduces Pandas, the primary Python library for data manipulation and analysis. It focuses on working with Series and DataFrame objects, performing data cleaning, and preparing structured datasets for machine learning and deep learning workflows.
The notebook includes practical examples covering:
- Creating and inspecting Series and DataFrames
- Data selection, filtering, and indexing
- Handling missing data
- Basic data aggregation and transformations
- Reading from and writing to common data formats
This chapter builds essential data wrangling skills required for preparing real-world datasets for PyTorch-based deep learning models.
This notebook introduces the core fundamentals of PyTorch, focusing on tensor creation, manipulation, and the foundational concepts required for deep learning workflows. It establishes the essential building blocks for working with tensors in PyTorch.
The notebook includes practical examples covering:
- Understanding tensors and their dimensions
- Creating PyTorch tensors
- Converting NumPy arrays to tensors
- Tensor indexing and reshaping
- Basic tensor operations
- Relationship between NumPy arrays and PyTorch tensors
This chapter lays the groundwork for building and training neural networks in subsequent deep learning modules.
This notebook presents foundational machine learning concepts required for understanding deep learning workflows. The chapter focuses on high-level theory and terminology that underpin supervised and unsupervised learning approaches.
The notebook includes conceptual notes covering:
- What is machine learning
- Types of machine learning
- Supervised vs. unsupervised learning
- Regression vs. classification problems
- Basic machine learning workflow and terminology
This chapter provides the theoretical context needed before progressing to building and training deep learning models in PyTorch.
Jose Portilla, PyTorch for Deep Learning with Python Bootcamp, Udemy.