- Python for ML applications
- ML libraries and tools
- Datasets
- Scikit learn
- TensorFlow
- Useful tools
- Others places to look for answers
Python for ML applications
- Python for beginners
- Learn to code: freecodecamp
- Python Like You Mean It
- Data Preprocessing in Python
- The Jupyter Notebook
- Better Heatmaps and Correlation Matrix Plots
ML libraries and tools
- Free online course on AI
- AI: Google
- ML course from Google
- Facebook field guide to ML
- Rules of Machine Learning
- Good Data Analysis
Datasets
Below you can find a list of resources to check for interesting datasets:
- https://archive.ics.uci.edu
- https://dataverse.harvard.edu/
- https://paperswithcode.com/
- https://datasetsearch.research.google.com/
- https://cloud.google.com/bigquery/public-data/
- https://registry.opendata.aws/
- https://www.kaggle.com/
- https://en.wikipedia.org/wiki/List_of_datasets_for_machine-learning_research
Scikit learn
We will be using Scikit-Learn for importing a variety of ML libraries, particularly in the first 4 weeks of the lecture. Here you can find additional online resources on the "smart" usage of this practical tool.
TensorFlow
Useful tools
- Seeing theory
- fastpages: blogging platform with extra features for Jupyter Notebooks
- Benchmarking Every Open Source Model
- Record for your model training
- Version Control System for Machine Learning Projects
- Pipeline tracking and production model management
- Gallery of interesting Jupyter Notebooks