- Learned about different Machine Learning models/libraries that can be used (Bag of Words, LSTM, BERT + BERT for classification problems.
- Learned how ML projects are run and the process behind designing ML models.
- Reviewed the Beautiful Soup and Selenium libraries in Python.
- Built my first very simple logistic regression model from a dataset that determined whether or not a tumor was malignant or benign.
- Explored data scraping.
- Google Colab + Jupyter Notebook (Gained familiarity)
- Kaggle (dataset on tumors)
- Beautiful Soup
- Debugging - found and corrected errors that I encountered in my code.
- Resourcefulness - used various sources to find information to get an idea of the NLP/ML models and how I could model one myself.
- Organization - organized my workspace and kept track of the various tasks that I was undertaking.
- Revisited both the Colab and Jupyter Notebooks: I have experience coding in Python in both notebooks and have done some basic AI in Colab, so I revisited both platforms just to make sure I was still able to use them properly.
- Explored the various uses of NLP and the general project flow for ML projects.
- Learned how to create my own Logistic Regression model and applied it to a specific set of data.