Teaching a deep neural network to play Go

Deep learning against humans Creating machines that can perform tasks better than humans has always been the dream behind artificial intelligence. A London-based company called DeepMind, had a breakthrough in 2015, when it produced a deep neural network, called AlphaGo, that …

Joshua Tenenbaum

Bayesian program learning

Human-level concept learning I am a huge fan of Joshua Tenenbaum and his research. Recently, he published in collaboration with Brenden Lake and Ruslan Salakhutdinov a new piece of research regarding “Bayesian Program Learning“. The paper is actually entitled “Human-level concept learning through probabilistic …

neural network wallpaper

Neural networks tips and tricks

Deep neural networks can be complicated to understand, train and use. Deep learning is still, to a large extent, an experimental science. This is why getting some input on the best practices can be vital in making the most out …

Performance Measures in Predictive Modelling

Issues with performance measures in machine learning When testing a predictive model, choosing the correct performance measure is imperative for making sure our model works correctly. In machine learning literature, however, it is common to use measures because they have always …

Engineering can be of different types

Data Science Protocols

Standardising data science

One of the main problems in data science practice is the lack of standardisation regarding procedures and techniques. Coming out of education and moving into the industry you can find yourself with knowledge of various methods and approaches, but no clear guide on best practices. Indeed, data science still largely remains an endeavour largely based on intuition and personal experience.

In other engineering disciplines there are standards to ensure the quality of the final result. Of course, data science is different to engineering disciplines such as civil engineering or computer engineering, where the final output is a physical product. Data science is closer to software engineering, where the lack of physical components means there are smaller  construction costs, and considerably more room to experiment and try different things out.

...