Repository contains the example code with the fundamentals of Machine Learning in python with Scikit-Learn and TensorFlow.
- The Fundamentals of Machine Learning:
- Lifesat - predict life satisfaction based on the GDP per capita.
- Housing - predict median house values in Californian districts, given a number of features from these districts.
- Classification - classification of the MNIST handwritten digits.
- Titanic - complete the analysis of what sorts of people were likely to survive.
- Spam Classifier - build a spam classifier.
- Training Linear Models - learn how to train linear models.
- Support Vector Machines - learn about support vector machines.
- Decision Trees - learn how to train, visualize, and make predictions with Decision Trees.
- Ensemble Learning and Random Forests - discover the most popular Ensemble methods, including bagging, boosting, stacking, Random Forests...
- Dimensionality Reduction - learn more about reduce dimensionality technique.
- Neural Networks and Deep Learning:
- Up and running with TensorFlow - learn more about powerful open source software library for numerical computation.
- Introduction to Artificial Neural Networks - learn more about artificial neural networks (ANNs).
- Training Deep Neural Nets - learn how to train deep DNNs.
- Distributed TensorFlow - learn how to how to use TensorFlow to distribute computations across multiple devices (CPUs and GPUs) and run them in parallel.
- Convolutional Neural Networks - learn more about CNNs.
- Recurrent Neural Networks - learn more about recurrent neural netwprks (RNN).