What do you think of when someone says "AI" or "Artificial Intelligence"? For most of us, it conjures up an image of the future. It doesn't much evoke the here and now. Artificial intelligence is already out of the box. And while it might not be as slick as the movies, it has vast applications in almost every field, from business to medicine, traffic jams to Facebook photos.

When I was working on my next pattern classification application, I realized that it might be worthwhile to take a step back and look at the big picture of pattern classification in order to put my previous topics into context and to provide and introduction for the future topics that are going to follow. Pattern classification and machine learning are very hot topics and used in almost every modern application: Optical Character Recognition (OCR) in the post office, spam filtering in our email clients, barcode scanners in the supermarket … the list is endless. In this article, I want to give a quick overview about the main concepts of a typical supervised learning task as a primer for future articles and implementations of various learning algorithms and applications. Predictive modeling is the general concept of building a model that is capable of making predictions. Typically, such a model includes a machine learning algorithm that learns certain properties from a training dataset in order to make those predictions.

I'm trying to find a website that this guy wrote. In it he explains how machine learning works, gives you a history of its evolution and you build an OCR example as part of the tutorial using the MNIST DATABASE as your sample set. I found this site on a friends computer and now I've lost it.

I'm struggling with math while I'm reading Machine learning: A probabilistic perspective like I'm confused about quantiles, inverse cdf etc. Could you recommend me a book that I should read first? The best STEM book I've ever read. Goes into great depth without sacrificing any ease of comprehension. Few recourses, in any subject, can provide both.

Today we have some very good AI/ML posts. First, Pete Warden tells us how to break into machine learning. It is some very practical advice on how to get started. David Lettier shows us how to develop K-Means from scratch. Lastly, on An Uncommon Lab we get to see how Kalman Filters work.

A couple have been told to restrain their cat or face having their mail deliveries suspended. Matthew Sampson was notified by Royal Mail last week of a "potential hazard" at his home in South Gloucestershire which was "affecting deliveries". According to Royal Mail, Bella the cat is a "threat" to staff and has been putting "fingers at risk of injury". But owner Matthew Sampson, said he was "shocked" by the notice as he has "never seen her get aggressive". In the letter, Royal Mail states it has been "experiencing difficulties in delivering mail" to Mr Sampson's address in Patchway "because of the actions of a cat". It said the couple's postman had reported that when he pushes mail through their letterbox their cat "snatches the mail and put his fingers at risk of injury".

Not surprisingly, the Guild isn't happy with the Supreme Court's choice -- it calls this a "colossal loss" and insists that the appeals court was "blinded" by Google's attempt to portray itself as rescuing lost books for the public good. The statements are a bit melodramatic (many of these titles are unlikely to return to print before they reach the public domain), but they do point out that the concerns over digitizing books aren't quite over. Although Google appears to have walked a fine line, the worry is that other outfits might not be quite so scrupulous.

The Authors Guild and several individual writers have argued that the project, known as Google Books, illegally deprives them of revenue. The high court left in place an October 2015 ruling by the 2nd U.S. Circuit Court of Appeals in New York in favor of Google. A unanimous three-judge appeals court panel said the case "tests the boundaries of fair use," but found Google's practices were ultimately allowed under the law. The individual plaintiffs who filed the proposed class action against Google included former New York Yankees pitcher Jim Bouton, who wrote the acclaimed memoir "Ball Four." Several prominent writers, including novelist and poet Margaret Atwood and lyricist and composer Stephen Sondheim, signed on to a friend-of-the-court brief backing the Authors Guild.

Fair use also allows for people to transform the original content into a new type of work, and that transformation of the printed books was part of Google's argument in this case. The group wanted the Supreme Court to "recognize Google's seizure of property as a serious threat to writers and their livelihoods, one which will affect the depth, resilience, and vitality of our intellectual culture," the Authors Guild said on a webpage detailing the case. The Supreme Court decision gave authors a "colossal loss," Authors Guild President Roxana Robinson said in a statement. Google Books project may lead to a short-term public benefit, but it will come at the expense of the future vitality of U.S. culture, Robinson added. "The denial of review is further proof that we're witnessing a vast redistribution of wealth from the creative sector to the tech sector, not only with books, but across the spectrum of the arts," she said.

A lot of people would struggle to get through their daily lives without the help of glasses, but for most, they help make everything they are looking at slightly clearer. But for one man, a new pair glasses is doing much more than that, allowing him to read for the first time in 20 years. Luke Hines was left blind in one eye and with only three per cent vision in the other after an operation to remove a childhood brain tumour in 1997. Luke Hines (pictured) was left blind in one eye and with only three per cent vision in the other after an operation to remove a childhood brain tumour in 1997. He was unable to attend school, has not found work because of his condition and has spent years feeling isolated.