Massachusetts Institute of Technology (MIT) hosts their entire 2010 course on artificial intelligence / machine learning by Professor Patrick Winston on YouTube. Although some parts seem already kind of dated seven years later, the videos on several evolving topics (e.g., Neural Networks) have been updated in the fall of 2015. The tutorial assignments you can…
Tag: video
Video: Bias in Machine Learning
Mainstream media have caught onto the difficulties of machine learning. Most saliently, they just love to report how AI and bots can be as racist, discriminatory, or biased as humans. Some examples: Microsoft’s racist Twitter bot (Verge, 2016) Gender-biased text mining AI (Guardian, 2017) Racist criminal profiling bot (ProPublica, 2016) Google’s Sentiment Analyzer Thinks Being…
Generating images from scratch: Parallel Multiscale Autoregressive Density Estimation
A while ago, I blogged about this new algorithm, pix2code, which takes in pictures of graphical user interfaces and outputs the underlying code. Today, I discovered another fantastic algorithm, by Scott Reed and his colleagues at Google Deepmind. txt2pix would be a catchy name for this algorithm, as it can take in a fairly complex sentence (e.g., “a…
Digitizing the Tour de France 2017
Combining two of my favorite things, Dimension Data elaborates on how they are using data, machine learning and predictive modeling to take the Tour de France experience to the next level in 2017. Eurosport already jumped on the bandwagon in 2016 with some amazing visualizations of common Tour scenarios. Here is one on how to win…
Veritasium: Bayes’ Theorem explained
Veritasium makes educational video’s, mostly about science, and recently they recorded one offering an intuitive explanation of Bayes’ Theorem. They guide the viewer through Bayes’ thought process coming up with the theory, explain its workings, but also acknowledge some of the issues when applying Bayesian statistics in society. “The thing we forget in Bayes’ Theorem is…