Project overview and quick guide to getting started.
Training Naive Bayes, Decision Tree, Random Forest, KNN, Multinomial Logistic Regression and Neural Network classifiers on the Iris data-set.
Building a Markov Model from source text and using it to generate new text.
Training a vanilla feed forward Neural Network on images of handwritten digits.
Learning to classify sentences as containing either positive or negative sentiment with Naive Bayes and Neural Networks.
Finding clusters of related documents with four different techniques - K Means, NNMF, Random Projections and SVD.
Getting a neural net to learn the rules of binary addition and how to use its memory to store carry bits as appropriate.
More complicated sequences call for more complicated neural networks. This tutorial shows how to use a GRU recurrent neural network to learn the Embedded Reber Grammar.
Using different recurrent neural network architectures for classifying sequential inputs such as one to many, many to one and sequence to sequence with Long Short Term Memory (LSTM)
Learning to recognise handwritten digits (MNIST) with convolutional neural networks gives a higher classification accuracy (and a longer training time)