By regression, I mean the derivation of a continuous property of an image (e.g. the mean area of the objects shown on the image) from its pixeldata. I'd like to train the algorithm with several images with known properties, in order to use it to analyze unknown images. From my limited understanding, this should be possible. Nevertheless, I only found examples of image classification or regressions of numerical values. Therefore, I'd be very thankful for hints to examples or tutorials.

We get asked a lot of questions about how to start building with Watson, so we decided to compile our top 4 Frequently Asked Questions. You can use this as a guide to learn more about the technology, receive inspiration from use cases, get valuable resources, and ultimately begin building with the technology. Cognitive technology's strength lies in its ability to draw insights from unstructured data sets. Structured data is found in a spreadsheet, whereas unstructured data is text such as tweets, medical journals, etc. Today 80% of data is unstructured, so tools such as cognitive computing are becoming more important in helping humans understand what's inside that data.

Software engineering is about developing programs or tools to automate tasks. Instead of "doing things manually," we write programs; a program is basically just a machine-readable set of instructions that can be executed by a computer. Let's consider a classic example: e-mail spam filtering. Assuming that we have access to the source code of our e-mail client and know how to handle it, we could come up with an instinctive set of rules that may help us with our spam problem. For example: if not "sender in contacts": if "subject line contains BUY!: e-mail spam folder:" else if ... It is intuitive to say that coming up with these rules is a pretty tedious task.

Everyone has an AI in their pocket these days -- Siri, Cortana, Google Now and Amazon's Alexa have given everyone easy access to virtual assistants. But one promising startup could wind up beating them all: Viv. Viv is still in its early stages, but it has caused a lot of excitement in the tech community, and according to a profile in The Washington Post, it has drawn bids from some major players. Here's what you need to know about Viv. Viv is poised to be the next big AI assistant.

The AI can compare the user's question with others that have already been asked, thus generating a more relevant answer. Let's say she opens a bot's FAQ and asks'how can I get new password?'. Note that the user has found the bot's FAQ. So a good user interface has led her to this point already. This is thus a good example of how UI and AI work well in combination.

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).