The key point is that we are not interested in all possible ML problems, most of them don't make any sense and will never occur with real data. Imagine I have a training and test set for a binary classifier, you can train a good algorithm and get 95% accuracy for the test set, now you flip the labels in the test set and the same algorithm that was excellent is a disaster. But there's a trick: the new problem doesn't make any sense. We are expecting the algorithm to learn how data works and then predict in the opposite direction. We don't have this problems with real data, they just don't make sense.

Over the years, artists, writers, filmmakers and game studios have all tackled the concept of artificial intelligence. Often their vision is of machines that are brutally hostile to humans. Philip K. Dick envisioned androids that murder their owners. Of course, there's Skynet, which launches an all-out war on mankind. We could go on like this for a long time. But there are also those, like Spike Jonze, who envision us having a more complex relationship with computer-based personalities; one in which they could even be love interests.

At the confluence of the rise in messaging applications, advances in text and language processing, and mobile form factors, bots are emerging as a key area of innovation and excitement. Bots (or conversation agents) are rapidly becoming an integral part of your digital experience--they are as vital a way for people to interact with a service or application as is a web site or a mobile experience. Developers writing bots all face the same problems: bots require basic I/O, they must have language and dialog skills, and they must connect to people--preferably in any conversation experience and language a person chooses. This code-heavy talk focuses on how to solve these problems using the Microsoft Bot Framework, a set of tools and services to easily build bots and add them to any application. We'll cover use cases and customer case studies for enhancing an application with a bot, and how to build a bot--focusing on each of the key problems: how to integrate with various messaging services, how to connect to users, and how to process language to understand the user's intent.

So I'm buliding a small list of many different ML libraries, but don't want to miss out too many (sure I will do some). Anything else which you are using and think needs attention please feel free post.

"Intelligent system designers do have ethical responsibilities." I have interviewed John Markoff, technology writer at The New York Times. In 2013 he was awarded a Pulitzer Prize. The interview is related to his recent book "Machines of Loving Grace: The Quest for Common Ground Between Humans and Robots, published in August of 2015 by HarperCollins Ecco. Do you share the concerns of prominent technology leaders such as Tesla's chief executive, Elon Musk, who suggested we might need to regulate the development of artificial intelligence?

Imagine you took a world-class business writer and asked him to rate the quality of several pieces of content in a blind test. Would he be able to tell which ones were created by humans and which ones were produced by automated writing? Well, that's exactly what Mark Schaefer addressed recently. To find out that… "two of the top three posts were written by a computer." Given that Mark is one of the most respected speakers and writers on marketing, with a successful blog, an impressive audience and numerous publications, I wouldn't blame you if it sounded so.

In 2014, Google acquired the artificial intelligence startup DeepMind, but it wasn't cheap. With a price tag of 500M, there must have been something special that Google saw in DeepMind that was worth acquiring. While the company hasn't produced any actual products for commercial use, they have focused on machine learning. Machine learning is a type of artificial intelligence that aims to provide computers with the ability to learn new information without being directed to do so. Machine learning involves the development of computer programs that have the ability to teach themselves to grow and alter themselves when presented with new data.

"Figuring out how to build ethical autonomous machines is one of the thorniest challenges in artificial intelligence today," researchers from the University of Toulouse and MIT's Media Lab argue in their paper in the journal Science on a survey that tries to work out how moral people want their self-driving cars to be. But is it the thorniest challenge? I'd argue the thorniest problem is working out some form of AI that is even capable of making ethical decisions. Self-driving algorithms have some way to go before we can even begin to consider whether they can weigh up the ethics of a situation along similar lines to Isaac Asimov's famous three laws. And you then have the knotty problem of determining what is truly ethical.

Here are some helpful R functions for regression analysis grouped by their goal. The name of package is in parentheses. Base has a method for objects inheriting from class "lm" (stasts) This is a generic function, but currently only has a methods for objects inheriting from classes "lm" and "glm" (stasts) AIC: Generic function calculating the Akaike information criterion for one or several fitted model objects for which a log-likelihood value can be obtained, according to the formula -2*log-likelihood k*npar, where npar represents the number of parameters in the fitted model, and k 2 for the usual AIC, or k log(n) (n the number of observations) for the so-called BIC or SBC (Schwarz's Bayesian criterion) (stats) Four plots (selectable by which) are currently provided: a plot of residuals against fitted values, a Scale-Location plot of sqrt{ residuals } against fitted values, a Normal Q-Q plot, and a plot of Cook's distances versus row labels (stats) Performs Bartlett's test of the null that the variances in each of the groups (samples) are the same (stats) bgtest: Breusch-Godfrey Test (lmtest) bptest: Breusch-Pagan Test (lmtest)

In September, San Diego robotics startup Brain Corporation will introduce artificial intelligence software that allows giant commercial floor-cleaning machines to navigate autonomously. The follow-up offering it wants to develop may be even more forward-looking: A training and certification program for janitors to operate the machines. The program, still in early stages of planning, is aimed at helping janitors maximize efficiency and establishing standards and best practices for the use of robots in janitorial work, according to Brain Corporation. The company says it is not aware any other such training program exists. There's additional incentive for Brain Corp. to offer training options.