Facial recognition makes sense as a method for your computer to recognize you. After all, humans already use a powerful version of it to tell each other apart. But people can be fooled (disguises! Now researchers have demonstrated a particularly disturbing new method of stealing a face: one that's based on 3-D rendering and some light Internet stalking. Earlier this month at the Usenix security conference, security and computer vision specialists from the University of North Carolina presented a system that uses digital 3-D facial models based on publicly available photos and displayed with mobile virtual reality technology to defeat facial recognition systems.

Sure, everyone loves a masterfully poured tulip doodle in their morning brew, but there's no need to photograph it for your friends -- again. It's alright, everyone runs out of photographic inspiration from time to time. Mostly leaning on hard-working artificial intelligence and neural networks deep in the back-end of the Internet -- Google's DeepDream being the big one -- these apps can turn your pet pictures into Picaso-esque portraits or your selfies into a scene out of "Starry Night." Check out the results of filtering the same image through the various apps below. They're all works of art, no paint required.

Travis Kalanick, CEO of Uber, recently spoke to USA TODAY about the company's new efforts to develop a self-driving ride-sharing vehicle with the help of Swedish automaker Volvo. "If we don't get the (autonomous car) software thing nailed, we're not going to be around much longer," the captain of the ride-hailing juggernaut told USA TODAY on Thursday. In his mind, self-driving cars are a societal inevitability that will reduce deaths, traffic and pollution. "Will it all take time and storytelling (to reassure consumers)? "But that's where it ultimately ends up." Kalanick, 40, spoke at Uber's sprawling headquarters here just hours after the company, privately valued at 66 billion, announced two major strategic moves aimed at better positioning itself for an autonomous vehicle future. Uber is rolling out the first of 100 Volvo SUVs equipped with self-driving features in Pittsburgh later this month, part of a 300-million partnership. Volvo has targeted 2021 for a self-driving car. And Uber is buying Otto, a 100-person startup focused on bringing autonomous features to tractor trailers. Kalanick insisted that neither deals -- nor Uber's recent sale of its UberChina operations to rival Didi Chuxing --were designed to make the company more attractive to investors for a possible initial public offering. "My statements on this have been well documented, but you gotta ask, I get it," said Kalanick in his characteristically direct style that blends pauses with declarative statements. "If there was a way to get mass liquidity without going public, (which is) that bureaucracy piece, then I'm super excited about that.

Creating original branded content solves many problems for marketers, but also presents challenges -- among them distribution and realizing ROI from what can be a costly investment. Time Inc., CBS and Telepictures are among hundreds of publishers working with IRIS.TV, which recently introduced a product to manage the distribution of branded content. Its video personalization solution uses artificial intelligence and machine learning technology so publishers can automate the programming of their video libraries for the individual based on that person's preferences and behavior. We spoke with Rohan Castelino, director of business development and marketing with IRIS.TV, about how this works. While brands are increasingly looking to partner to create content to engage Millennials, how can publishers deliver guaranteed audiences to watch this content at scale while maintaining their editorial standards and trust with audiences?

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries--Nigeria, Tanzania, Uganda, Malawi, and Rwanda--we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.

Following a survey we did back in 2014, I posted on Finextra about how machine learning technologies are progressing from academia, robotics and medical engineering into financial services. At that time, there seemed to be some hesitancy with only 12% of 80 quant-savvy finance professionals saying they used machine learning in their workflows. Has Use of Machine Learning Changed? To provide some answers, we decided to survey attendees at our 2016 finance conference. Our sample was mainly made up of numerically- and model-led quant roles and risk management roles and therefore those most likely to use machine learning.

An anonymous reader quotes a report from Network World discussing Nvidia's project called DAVE2, where their engineering team built a self-driving car with one camera, one Drive-PX embedded computer and only 72 hours of training data: Neural networks and image recognition applications such as self-driving cars have exploded recently for two reasons. First, Graphical Processing Units (GPU) used to render graphics in mobile phones became powerful and inexpensive. GPUs densely packed onto board-level supercomputers are very good at solving massively parallel neural network problems and are inexpensive enough for every AI researcher and software developer to buy. Second, large, labeled image datasets have become available to train massively parallel neural networks implemented on GPUs to see and perceive the world of objects captured by cameras. The Nvidia team trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands.

Here's What We Can Expect from Deep Learning in 2016 and Beyond Is Humanising Chatbots the Next Inevitable Improvement?

Here's What We Can Expect from Deep Learning in 2016 and Beyond Is Humanising Chatbots the Next Inevitable Improvement?