In which we see how a neural network can "paint" a picture that combines the content of one image with the style of another.
In which we investigate convolutional neural networks, and train one with TensorFlow to distinguish cats from dogs.
In which we understand the capabilities of different machine learning techniques by illustrating their solutions to randomly generated classification problems
In which we discuss, code then visualise an autoencoder for learning the component visual features of handwritten digits.
Notes on probabilistic graphical models with reference to the Titanic disaster (the movie AND the boat)
In which we examine the strengths of probabilistic graphical models and build one to predict the survival of Titanic passengers.
In which we play with movie genre data from IMDB.com and draw a chart of animated grass
In which we use D3.js to make a zoomable treemap of books in the Dewey Decimal System
A method for adaptive, supervised learning when you have streaming data.
In which we use Python's SymPy library to manipulate the laws of physics.
In which we do a Bayesian optimal search of Italy using Roman scouts.
In which we use Bayesian regression to automatically adapt to the wartime shocks to Britain’s bread price.
In which we are archaeologists learning about how the Bayesian method mathematically encodes deductive reasoning.
In which we use Bayesian methods to figure the most likely breed of dog for Dogmatix.
In which Robot Fyodor Dostoyevsky says, "It's night I am in my room with a candle and suddenly there are devils all over the place in the paling where you can take a board out he gets through no one sees ."
In which we use Python to teach a computer the difference between three types of fiction.