Politics is a distracting affair which I generally believe it’s best to stay out of if you want to be able to concentrate on research. Nevertheless, the US presidential election looks like something that directly politicizes the idea and process of research by damaging the association of scientists & students, funding for basic research, and creating political censorship.

Alphabear is a fun puzzle game in which you spell words, and collect cute bears that help boost your score. You can progress through levels and challenges. Some challenges are tough, so I ended up coding some queries to help me get past them. Here’s a tool I wrote.

Recently we (Alex & Tatiana) were invited to give lectures about machine learning at GradDays — an event that is organized twice a year at the Heidelberg University (Germany’s oldest university).

The emergence of “Big Data” has made machine learning much easier because the key burden of statistical estimation—generalizing well to new data after observing only a small amount of data—has been considerably lightened. In a typical machine learning task, the goal is to design the features to separate the factors of variation that explain the observed data. However, a major source of difficulty in many real-world artificial intelligence applications is that many of the factors of variation influence every single piece of data we can observe. Deep learning solves this central problem via representation learning by introducing representations that are expressed in terms of other, simpler representations.

1 - Introduction

It’s a widely cited fact that Uber has continually lost money since it started. Uber opponents widely cite this fact hoping that once the VCs stop investing, Uber will collapse and we can return to the era of yellow cabs. Another stylized fact about Uber is that it’s profitable in many cities. In this post I’m going to do some basic financial modeling, and explain why these two facts make me very bullish on Uber.

The original goal of this post was to explore the relationship between the softmax and sigmoid functions. In truth, this relationship had always seemed just out of reach: “One has an exponent in the numerator! One has a summation! One has a 1 in the denominator!” And of course, the two have different names.

I’ve trained a sentiment analysis on simple data set:

It is spring, and the flowers bloom. One tree in particular symbolises this: the Japanese cherry (sakura) tree. Every year, millions of Japanese enjoy hanami, jointly watching the cherry blossoms, philosophising about the the transient nature of beauty, and the inevitability of death.