According to Musk, only one company scares him (he would not mention names, but Google is in the "pipe"). The danger is the following: an organization (company, group of individuals, government, etc ..) manages to create an AI with great intelligence and uses it for its own purposes. According to the intentions of the owner, this monopoly could lead to very negative consequences for our society.

Google-owned artificial intelligence company DeepMind presented a deep neural network that generates amazingly human-like speech. Called WaveNet, this AI makes a significant advancement over existing speech synthesizers. What's more, it can write pretty good classical music. DeepMind is a British company, previously known for creating machine-learning AI software that beat the world champion of the notoriously-intricate game Go. Machine learning allows computer systems to teach themselves and make predictions based on gathered data.

Researchers from Karlsruhe Institute of Tech, MIT and University of Toronto published MovieQA, a dataset that contains 7702 reasoning questions and answers from 294 movies. Their innovative dataset and accuracy metrics provide a well-defined challenge for question/answer machine learning algorithms. The questions range from simpler'Who' did'What' to'Whom' that can be solved by computer vision alone, to'Why' and'How' something happened in the movie, questions that can only be solved by exploiting both the visual information and dialogs. MovieQA is unique in that it contains multiple sources of information – full-length movies, plot synopses, subtitles, scripts and DVS (a service that narrates moves scenes to the visually impaired). With the need to scale to large vocabulary data sets, they relied on a TITAN Black GPU for their overwhelming amount of training data.

Two of today's major business and intellectual trends offer complementary insights about the challenge of making forecasts in a complex and rapidly changing world. Forty years of behavioral science research into the psychology of probabilistic reasoning have revealed the surprising extent to which people routinely base judgments and forecasts on systematically biased mental heuristics rather than careful assessments of evidence. These findings have fundamental implications for decision making, ranging from the quotidian (scouting baseball players and underwriting insurance contracts) to the strategic (estimating the time, expense, and likely success of a project or business initiative) to the existential (estimating security and terrorism risks). The bottom line: Unaided judgment is an unreliable guide to action. Consider psychologist Philip Tetlock's celebrated multiyear study concluding that even top journalists, historians, and political experts do little better than random chance at forecasting such political events as revolutions and regime changes.1 The second trend is the increasing ubiquity of data-driven decision making and artificial intelligence applications. Once again, an important lesson comes from behavioral science: A body of research dating back to the 1950s has established that even simple predictive models outperform human experts' ability to make predictions and forecasts. This implies that judiciously constructed predictive models can augment human intelligence by helping humans avoid common cognitive traps.

APPLE's events have often been compared to religious worship. Evangelical fans watch as the company's darkly-clad boss--first Steve Jobs, now Tim Cook--presents shiny new iSomethings in front of a screen showing colourful slides reminiscent of stained glass. Yet Apple's latest event, on September 7th, was a less rapturous affair. The iPhone 7, the firm's new smartphone, will come with a better camera, a faster chip and a brighter display, but will otherwise not be much of an improvement. The main novelty is that it no longer has a conventional jack for headphones, which have to plug into the charging port or be wireless (conveniently, Apple also introduced new untethered "AirPods", which will cost 160 a pair).

There are few subjects in computing as fascinating, or intimidating, as machine learning. Let's face it -- you can't master machine learning in a weekend, and at the very least it requires a good grasp of the underlying mathematical principles. That said, if you have the math chops, you'll want to augment your use of machine learning frameworks (there are plenty to pick from) with a good understanding of the theory behind them. Here are five high-quality, free-to-read texts that provide introductions to and explanations of machine learning's ins and outs. Some have code examples, but most focus on formulas and theory; in principle, they can be applied to any number of languages, frameworks, or problems.

In my last post, I showed how to find similar Game of Thrones episodes based on the characters that appear in different episodes. This allowed us to find similar episodes on an episode by episode basis, but I was curious whether there were groups of similar episodes that we could identify. A clustering algorithm groups similar documents together, where similarity is based on calculating a'distance' between documents. Documents separated by a small distance would be in the same cluster, whereas if there's a large distance between episodes then they'd probably be in different clusters. The KMeans algorithm clusters data by trying to separate samples in n groups of equal variance, minimizing a criterion known as the inertia or within-cluster sum-of-squares.

Over the past 30 years, tools once reserved for presidents, spies, generals and media moguls have been made available cheaply to billions. Streaming live video to a global audience used to cost millions. Now, it's free and you could be doing it in five seconds if you wanted to. Every great leader, from presidents to CEOs, is surrounded by trusted advisors who guide and inform at every step. Successful leaders often succeed in part because they have better advice or better information.

With every new technology and paradigm, there are a lot of misconceptions, but I'll try to set the record straight about the most common ones concerning bots. Wrong, most bots do not currently use AI, a lot of them will never need to use AI. Some bots use Natural Language Processing/Understanding to map what the user is saying to the bot to an actual intent. For example, there are many ways to say you want to book a ticket to a movie -- "I wanna book a ticket for later this evening", "I want to go to the movies tonight", "book me a ticket to a movie after 8pm"- all of these mean more or less the same, but for a developer it is quite hard to map these into an intent to book a ticket this evening. That is the most common use of AI today in bots, this is not what most people think about when they say artificial intelligence.

In 2014 Google bought a UK-based artificial intelligence research lab called DeepMind for a hefty 530 million. Since then, DeepMind has made rapid progress in AI technologies, including health and gaming applications. The latest achievement of DeepMind is WaveNet, an AI computer program that can almost mimic the way humans speak. Experts say that WaveNet has "halved" the gap between machine-speak and a natural human voice. So what we're talking about here is more like Jarvis from Iron Man than Arnold Schwarzenegger in Terminator – or any of his other movies, for that matter!