This repository contains the code I wrote while taking the TensorFlow for Deep Learning course by Daniel Bourke. It includes the Jupyter/Colab notebooks and code that I developed as I followed along with Daniel during the course, applying deep learning concepts using TensorFlow.
Before diving into the TensorFlow for Deep Learning course, I started the Stanford University Machine Learning course by Andrew Ng. While it provided a strong theoretical foundation, I realized that I needed something more hands-on to effectively apply machine learning concepts. This led me to discover Daniel Bourke’s course, which offers a more practical approach to deep learning, and I’ve found it to be a better fit for my learning style.
I started the TensorFlow for Deep Learning course around February 2021 and worked through it until June. However, I encountered some challenges along the way, particularly with tasks like data cleaning and my general understanding of data analytics. I realized that having a solid foundation in data analysis would greatly enhance my comprehension of machine learning systems. As a result, I paused the course to complete the Google Data Analytics Professional Certificate, which provided me with a strong understanding of data analysis and working with data. With this newfound knowledge, I’m now back to the TensorFlow for Deep Learning course and continuing from where I left off, starting with Transfer Learning, building machine learning and deep learning models that solves real world problems.
The TensorFlow for Deep Learning course is designed to introduce deep learning concepts and techniques using TensorFlow, one of the most popular frameworks for building machine learning models. In this course, I learned how to build and optimize models for various applications, such as image classification and natural language processing.
Key Topics Covered: Introduction to TensorFlow Neural Networks & Deep Learning Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) Transfer Learning Model Optimization & Evaluation Solving real-world ML and DL problems with TensorFlow
I would like to express my appreciation to Andrew Ng for his invaluable contribution to the field of machine learning through the Stanford University Machine Learning course. His course served as an excellent theoretical foundation and sparked my interest in deep learning, which eventually led me to explore more practical approaches, such as the TensorFlow for Deep Learning course by Daniel Bourke.
Special thanks to Daniel Bourke for providing the course and for the clear and insightful explanations. Without his guidance, this repository would not have been possible.
I would like to express my gratitude to the Google team for creating the Google Data Analytics Professional Certificate. The course provided me with a comprehensive understanding of data analysis and has greatly enhanced my ability to work with data, which has been instrumental in my progress with deep learning.