A data scientist’s job hunt visualised

Sankey diagrams show the flow through a system, where the width of the bands is proportional to the flow quantity. The diagrams are named after Captain Matthew Henry Phineas Riall Sankey. In 1898, Sankey created a diagram showing the energy efficiency of a steam engine. The widths of the bands showed the gas, electric and coal energy flowing through …

Continue reading

Google DeepDream – turning a neural network inside out

Modern convolutional neural networks, like the one we built in the previous post are trained to detect faces or other objects in images. With multiple layers in a neural network, it can be difficult to understand how exactly the neurons in the network respond and activate to patterns in an image. One way to understand …

Continue reading

An Introductory Guide to Deep Neural Networks

Algorithms designed by deep learning methods have featured extensively in recent headlines. AlphaGo, developed by the Google DeepMind team was the first computer program to beat professional Go play Lee Sedol in a five-game match. Go has significantly more branching moves than chess, so traditional AI methods were unable to outperform human players. AlphaGo’s superhuman …

Continue reading