My journey into data science began early in 2023, driven by curiosity to learn something new. At the time, data science and machine learning were trending topics in marketing campaigns, tech forums, and discussions, so I decided to explore this fascinating field. I started with basic online videos to understand what data science was all about and what it would take to learn. I knew that mastering data science could eventually lead to advanced topics like machine learning and deep learning.
To lay the groundwork, I ordered a few books on data analytics and statistics, including the famous Naked Statistics. After just two to three months of foundational learning, I was eager to start applying my knowledge. I moved on to the book “Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow”, which included hands-on exercises. The early problems were manageable and introduced me to Python libraries like Pandas and NumPy, but as I progressed, the concepts became more challenging. Around the 70-page mark, I found myself slowing down, realizing the need to dedicate more time and patience to absorb the information fully.
.
Around this time, I also consulted with a professional data scientist friend. He introduced me to real-world concepts like imbalanced datasets and model performance metrics. While I couldn’t fully grasp these ideas then due to my limited foundation, they planted seeds for the areas I would revisit later. He emphasized that there are no shortcuts in this field and that persistence and effort are key.
In parallel, I explored Kaggle to accelerate my learning process. Following the projects and analyzing datasets helped me understand how advanced techniques were used in data analysis. As a beginner, I couldn’t contribute much, but I focused on understanding the code written by others while strengthening my basics with Pandas for data manipulation and Matplotlib for visualization. This phase helped me bridge the gap between theory and application.
Midway through 2023, I discovered the AWS Machine Learning Specialty certification, which offered a structured timeline and goal. I began preparing for it by studying a primary book and exploring AWS SageMaker, where I created small projects in image classification and segmentation. Although these projects weren’t comprehensive, they gave me hands-on experience with SageMaker’s ecosystem. During this period, I gained a better understanding of how models are evaluated, the metrics used, and the operational challenges of deploying machine learning solutions. This experience boosted my confidence to tackle real-world problems from a more focused perspective.
In March 2024, I successfully earned the AWS certification. With a stronger foundation, I revisited topics like model evaluation and imbalanced datasets, this time paying closer attention to the details. I also delved into advanced topics in deep learning, inspired by Andrew Ng’s online course. The course provided structured labs, making it easier to experiment with neural networks. Completing the labs and earning the certification further solidified my understanding of deep learning.
By October 2024, I felt ready to revisit mathematical concepts and worked on models like linear regression, focusing on the math behind fitting a line for linearly related points. This led me to a realization: while demos and tutorials are helpful, learners often need access to deeper explanations of the foundational math. This sparked the idea of creating a companion website to complement video tutorials. I wanted to build a resource where learners could watch videos for practical insights and refer to blogs for detailed mathematical explanations.
In December 2024, I began planning both the videos and the website. The videos would cater to professionals with programming knowledge and a basic math foundation, starting with linear regression, progressing to classification models, and eventually covering deep learning. The website would serve as a companion, providing in-depth explanations, so viewers wouldn’t need to rewatch videos to grasp complex concepts. Recognizing the effort required to build such a platform, I decided to open it up for contributions from others interested in learning and sharing knowledge.
As I move forward, my goal is to create a collaborative platform where aspiring data scientists can find resources, contribute, and learn together. This journey has taught me that persistence, curiosity, and a willingness to revisit the basics are key to mastering data science. I’m excited to share my experiences and help others on their learning path.
