Machine Learning with Python

A collection of Jupyter Notebooks with example projects from the book "Hands-on Machine Learning with SciKit-Learn, Keras & TensorFlow", 2nd edition, Aurélien Géron.

Note: these notebooks are meant only for demonstration porpouses. For the sake of simplicity, the data files (and everything except the notebooks) were not uploaded to the repository.

Projects in this repository

1. Housing Prices Predictor: introduction of regression models and techniques for data analysis and dataset segmenting
2. MNIST: data analysis for classification tasks and general classification techniques applied in the MNIST dataset
3. Titanic Classificator: creating a model for the task of classifying if a given passenger from the Titanic survived or not
4. Ensembled Learning: experimenting with different ensembling techniques in the MNIST dataset
5. Dimensionality Reduction: dimensionality reduction algorithms for increasing performance and generating data visualisations
6. Unsupervised Learning: algorithms for general unsupervised learning tasks and anomaly detection
7. Keras Intro: introduction of Neural Networks, trained on the MNIST dataset
8. Deep Neural Networks: general techniques (normalization/regularization) for dealing with the learning in Deep Neural Networks
9. CNNs for Computer Vision: using Convolutional Neural Networks for classifying landscapes (taken from Google Images)
10. RNNs Intro: using Recurrent Neural Networks for classification in a dataset of sketches (QuickDraw)