During my time in the Bytewise Fellowship program, I had the opportunity to explore into various topics and expand my knowledge in the field of Data Science and AI.
-
Tyler's Machine Learning Guide Episodes: As part of the fellowship, I had the opporutinty to listen to Tyler's Machine Learning Guide episodes. These informative and engaging episodes provided me with valuable insights into the fundamental concepts and techniques of machine learning.
-
Andrew NG's Introduction to AI: I also had the chance to study Andrew NG's Introduction to AI course. Andrew NG course provided a comprehensive overview of artificial intelligence, covering topics such as neural networks, reinforcement learning etc.
-
GitHub and Git: As part of the fellowship, I learned and practiced using GitHub and Git. These tools are essential for version control and collaboration in software development projects. I gained hands-on experience in creating repositories, managing branches, and merging changes.
-
Writing Medium Articles: During the program, I honed my technical writing skills by contributing articles to Medium. This experience allowed me to share my knowledge and insights with a wider audience while enhancing my ability to communicate complex concepts in a clear and concise manner.
I wrote an artice on why virtual environments are important and how to create it: https://medium.com/@shahood.sajid/guide-to-virtual-environments-for-python-8485530e7d2
-
Python: One of the focal points of the fellowship was learning and practicing Python programming. Python is a versatile and powerful language widely used in data science and machine learning. I gained proficiency in Python and applied it in various projects throughout the program.
-
Object-Oriented Programming (OOP) in Python: I also delved into object-oriented programming (OOP) in Python. I learned how to design classes, create objects, and implement inheritance, encapsulation, and polymorphism in Python.
-
Data Science Libraries: I explored popular data science libraries such as NumPy, Pandas, Matplotlib, and Seaborn. These libraries are essential for data manipulation, analysis, visualization, and statistical modeling. Through hands-on exercises and projects, I gained a solid understanding of these libraries and their applications in real-world scenarios.
-
Employee Classification Dataset: As part of my practical training, I worked on an employee classification dataset. This project involved using various machine learning techniques to predict whether an employee will be fired or not. It allowed me to apply my knowledge of data science and machine learning to a real-world problem.
-
Flower Classification: I also worked on a deep learning project. This project involved using VGG-16 deep learning model to classify 5 different flowers. It allowed me to explore how deep learning model are implemented and also learned how to tune it.
-
Logistic Regression: I learned logistic regression, used for binary classification problems. I studied its underlying principles, mathematical formulation, and implementation in Python.
-
MLops and Hugging Face Papers: To stay up-to-date with the latest advancements in the field, I deep dived into the trending topics of MLops and Hugging Face papers.