Machine learning fundamentals
Pre-requistes: Python language and its libraries Widely used Libraries - numpy, pandas, matplotlib, Scikit-learn, SciPy, Seaborn, Tensorflow.
You can use Visual Studio code (IDE) for python by downloading python extension in VS code. Jupiter notebook environment (.ipynb) within VS code which is a code level editor.
Google Colab is even better - free, cloud-based Jupyter Notebook environment, allows to write and execute Python code through the browser, especially suited for machine learning, data analysis. Also provides an online integrated development environment (IDE) for Python that requires no setup and runs entirely in the cloud. URL - colab.research.google.com
Helpful links: paperswithcode - research papers on AI https://www.kaggle.com/ - data science platform and online community for data scientists and machine learning practitioners, contains datasets, models, etc.. https://archive.ics.uci.edu/ - Well-known and widely used machine learning dataset repositories platform.
Machine learning stages:
- Business use case
- Data curation
- Data transformation
- Experimentation
- Model registry
- Model deployment
- Model monitoring