Artificial intelligence (AI, also machine intelligence, MI) is intelligence demonstrated by machines, in contrast to the natural intelligence (NI) displayed by humans and other animals. In computer science AI research is defined as the study of “intelligent agents”: any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term “artificial intelligence” is applied when a machine mimics “cognitive” functions that humans associate with other human minds, such as “learning” and “problem solving”.

Demystifying neural style transfer

About applying one image style to another and how it happens.

Learning social conventions in Markov games

This is some fun Facebook research on learning to behave. Mimicing and learning social conventions within the framework of game theory, such a nice idea. 

Q-learning

The simple q-learning approach to reinforcement learning.

Stumbling bots

Some remarks on chatbots and findings after more than seven years of research in this direction.

Interpretable discovery in large image datasets

As more and more data is collected by science, industry, finance, and other fields, the need increases for automated methods to identify content of interest.

Textual entailment

How logical consequences can be understood in NLP.

The classic NLU toolkit

Intro Traditionally, work in natural language processing has tended to view the process of language analysis as being decomposable into a number of stages, mirroring the theoretical linguistic distinctions drawn between SYNTAX, SEMANTICS, and…