Back when we were reading Karl Popper’s Logic of Scientific Discovery and Thomas Kuhn’s Structure of Scientific Revolutions, who would’ve thought that we’d be living through a scientific revolution ourselves?

Import AI: 108: Learning language with fake sentences, Chinese researchers use RL to train prototype warehouse robots; and what the implications are of scaled-up Neural Architecture Search

As more and more collections of data are becoming available on the web to everyone, non expert users demand easy ways to retrieve data from these collections. One solution is the so called Visual Query Systems (VQS) where queries are represented visually and users do not have to understand query languages such as SQL or XQuery. In 1996, a paper by Catarci reviewed the Visual Query Systems available until that year. In this paper, we review VQSs from 1997 until now and try to determine whether they have been the solution for non expert users. The short answer is no because very few systems have in fact been used in real environments or as commercial tools. We have also gathered basic features of VQSs such as the visual representation adopted to present the reality of interest or the visual representation adopted to express queries. A Survey on Visual Query Systems in the Web Era (extended version)

For several years now, few articles about artificial intelligence in the popular press are published without being accompanied by a picture of a Terminator robot. The point is clear: artificial intelligence is coming and it is terrifying.

“R is certainly becoming more and more popular, and seems to have found widespread adoption within many statistical research communities. This is a great thing as it means as new statistical methods or practices come out of the research world, they are often implemented and available in R. In many cases they have been written by the person who “wrote the book” (or paper) on a given topic.” Pete Werner ( March 14, 2015 )

The Homeland Security Department is investing in machine learning technology that could help foreign countries increase airport security at zero cost.

We present a rational analysis of curiosity, proposing that people’s curiosity is driven by seeking stimuli that maximize their ability to make appropriate responses in the future. This perspective offers a way to unify previous theories of curiosity into a single framework. Experimental results confirm our model’s predictions, showing how the relationship between curiosity and confidence can change significantly depending on the nature of the environment. A rational analysis of curiosity

Back when we were reading Karl Popper’s Logic of Scientific Discovery and Thomas Kuhn’s Structure of Scientific Revolutions, who would’ve thought that we’d be living through a scientific revolution ourselves?

Forecasting the evolution of events over time is essential to many applications, such as option pricing, disease progression, speech recognition, and supply chain management. It is also notoriously difficult: The goal is not just to predict an overall outcome but instead a precise sequence of events that will happen at specific times. Niels Bohr, a physics Nobel laureate, famously said that “prediction is very difficult, especially if it’s about the future.” In this blog post I will explore advanced techniques for time series forecasting using deep learning approaches on AWS. The post focuses on arbitrary time series value prediction so will be of interest to any reader working with time series. The post assumes that the reader already possesses basic technical knowledge in the field of Machine Learning.**