That's an interesting question, and I try to answer this is a very general way. The tl;dr version of this is: Deep learning is essentially a set of techniques that help we to parameterize deep neural network structures, neural networks with many, many layers and parameters. And if we are interested, a more concrete example: Let's start with multi-layer perceptrons (MLPs) … On a tangent: The term "perceptron" in MLPs may be a bit confusing since we don't really want only linear neurons in our network. Using MLPs, we want to learn complex functions to solve non-linear problems. Thus, our network is conventionally composed of one or multiple "hidden" layers that connect the input and output layer.

In the near future, artificial intelligence may well disrupt the way Frequently Asked Questions (FAQ) software is conceived. Naturally we are accustomed to traditional forms of FAQ with a simple user interface that reveals questions and answers. Not so long ago, IBM revealed the idea behind Watson, a system that is capable of processing natural language and machine learning in order to uncover insights and "help connect the dots." These types of systems are able to analyze huge amounts of data and extract meaning for future reuse and consultation. This natural form of "assembling" questions and answers was not possible decades ago.

Chatbots are on the rise, but what are they and why is everyone talking about (and to) them? Facebook has just rolled out support for bots on its Messenger platform. Meanwhile, Microsoft has described chatbots as the "new apps" with chief executive Satya Nadella saying that they "unlock conversation as a platform". The BBC "created" its own one-off chatbot to answer some of the burning questions you may have about this latest technology. What can I help you with Jane?

Chatbots are on the rise, but what are they and why is everyone talking about (and to) them? Facebook is widely expected to launch an app store for chatbots at its developer conference this week. Meanwhile, Microsoft has described chatbots as the "new apps" with chief executive Satya Nadella saying that they "unlock conversation as a platform". The BBC "created" its own one-off chatbot to answer some of the burning questions you may have about this latest technology. What can I help you with Jane?

Yesterday, news emerged that Google was using a machine-learning artificial intelligence system called "RankBrain" to help sort through its search results. Wondering how that works and fits in with Google's overall ranking system? Here's what we know about RankBrain. The information covered below comes from three sources. First, the Bloomberg story that broke the news about RankBrain yesterday (see also our write-up of it).

This article studies Frequency Adjusted Q-learning (FAQ-learning), a variation of Q-learning that simulates simultaneous value function updates. The main contributions are empirical and theoretical support for the convergence of FAQ-learning to attractors near Nash equilibria in two-agent two-action matrix games.The games can be divided into three types: Matching pennies, Prisoners' Dilemma and Battle of Sexes. This article shows that the Matching pennies and Prisoners' Dilemma yield one attractor of the learning dynamics, while the Battle of Sexes exhibits a supercritical pitchfork bifurcation at a critical temperature, where one attractor splits into two attractors and one repellent fixed point. Experiments illustrate that the distance between fixed points of the FAQ-learning dynamics and Nash equilibria tends to zero as the exploration parameter of FAQ-learning approaches zero.

This article describes FAQ FINDER, a natural language question-answering system that uses files of frequently asked questions as its knowledge base. Unlike AI question-answering systems that focus on the generation of new answers, FAQ FINDER retrieves existing ones found in frequently asked question files. Unlike information-retrieval approaches that rely on a purely lexical metric of similarity between query and document, FAQ FINDER uses a semantic knowledge base (WORDNET) to improve its ability to match question and answer. We include results from an evaluation of the system's performance and show that a combination of semantic and statistical techniques works better than any single approach.