Camera relocalization plays a vital role in many computer vision, robotics, augmented reality (VR) and virtual reality (AR) applications. In the real world, camera relocalization has empowered the recent consumer robotics products such as Dyson 360 Eye and iRobot Roomba 980 to know where they have previously visited [1]. In AR/VR products such as Hololens and Oculus Rift, camera relocalization helps to correctly overlay visual objects in an image sequence or real world. Scene Coordinate Regression Forests (SCRF) [2] is the pioneer in using machine learning for camera relocalization. In this method, a regression forest is trained to infer an estimate of each pixel's correspondence to 3D points in the world coordinate. Then these correspondences are used to infer the camera pose with a robust optimization scheme. Since then, various machine learning based methods, mainly random forests based [3], [4], [5], [6], [7], [8], [9] and deep learning based methods [10], [11], [12], [13], [14], [15] have been proposed to accelerate the progress of camera relocalization, in parallel with the traditional but still active featurebased methods [16], [17] and key-frame based methods [18], [19]. In these random forests based methods, either RGB-D/RGB pixel comparison features [2], [3], [5], [7], or the sparse features such as SIFT [8] are employed, without considering the spatial structure.

What neural network is appropriate for your predictive modeling problem? It can be difficult for a beginner to the field of deep learning to know what type of network to use. There are so many types of networks to choose from and new methods being published and discussed every day. To make things worse, most neural networks are flexible enough that they work (make a prediction) even when used with the wrong type of data or prediction problem. In this post, you will discover the suggested use for the three main classes of artificial neural networks. When to Use MLP, CNN, and RNN Neural Networks Photo by PRODAVID S. FERRY III,DDS, some rights reserved.

According to the Times, true artificial intelligence is just around the corner. A year ago, the paper ran a front-page story about the wonders of new technologies, including deep learning, a neurally-inspired A.I. technique for statistical analysis. Then, among others, came an article about how I.B.M.'s Watson had been repurposed into a chef, followed by an upbeat post about quantum computation. On Sunday, the paper ran a front-page story about "biologically inspired processors," "brainlike computers" that learn from experience. This past Sunday's story, by John Markoff, announced that "computers have entered the age when they are able to learn from their own mistakes, a development that is about to turn the digital world on its head."

This article is part of Demystifying AI, a series of posts that (try to) disambiguate the jargon and myths surrounding AI. The Wall Street Journal recently ran a piece that detailed how companies that provide email-based services scan the inboxes of millions of Gmail users. Their service agreements make it clear that they require access to your email so that their artificial intelligence algorithms can provide you with smart features such as price comparisons, automated calendar scheduling and more. What they don't tell you is that in some cases, their employees read your emails too, because their AI just can't perform as promised and it needs humans to fill the gap where it falls short. One of the companies presented in the Wall Street Journal article uses AI to add a "smart reply" feature to your email, which can make a big difference if you're managing your account from a mobile device.

Recently, Deep Learning models are being used in online learning applications. The online learning in such systems is achieved using different AI techniques such as Reinforcement Learning, or online Neuro-evolution. A limitation of such systems is the fact that the contribution from the Deep Learning model can only be achieved if the domain of use can be mostly experienced during the off-line learning period. Once the model is generated, it remains static and not entirely robust to changes in the application domain. A good example of this is in ecommerce applications–seasonal changes or short sales periods on ecommerce websites would require a deep learning model to be taken offline and retrained on sale items or new stock.

Hokkaido-Ya Restaurant in Singapore has deployed AI-powered kiosks from TabSquare. SmartKiosks use AI to identify customers and analyze guests' dining patterns and preferences. This aims to help the restaurant gain better understanding of guest behavior so more personalized meal recommendations can be given. The AI uses consumer data and deep learning algorithms in a bid to enrich the dining experience and help restaurants increase profitability. Guests interacting with the kiosks can now get personalized menu recommendations and promotions by simply entering their phone number or through a smart facial recognition option.

Chinese e-commerce giant Alibaba has developed an AI tool (artificial intelligence) capable of producing 20,000 lines of content per second. Created as part of Alibaba's digital marketing unit Alimama, the tool aims to reduce the heavy and arduous workload of producing copy for product listings by retailers, working by scraping "millions" of existing human writing samples from the company's e-commerce platforms which it interprets using deep-learning models and natural language processing (NLP) technologies. According to Alibaba, the AI tool has passed the Turing Test where a machine is analysed for its ability to imitate a human without detection and is already being used "millions of times a day" by retailers on its properties including Tmall, Mei.com, 1699.com and Taobao. Global fashion brands Esprit and Dickies are two such retailers already using the tool, which can be accessed by selecting an option to'Produce Smart Copy', allowing them to choose from samples of varying tones including "promotional, functional, fun, poetic, or heartwarming". While the release of Alibaba's AI tool will be welcome news for retailers, it may result in some sweaty palms among copywriters.

Machine learning is everywhere these days, but it's usually more or less invisible: it sits in the background, optimizing audio or picking out faces in images. But this new system is not only visible, but physical: it performs AI-type analysis not by crunching numbers, but by bending light. It's weird and unique, but counter-intuitively, it's an excellent demonstration of how deceptively simple these "artificial intelligence" systems are. Machine learning systems, which we frequently refer to as a form of artificial intelligence, at their heart are just a series of calculations made on a set of data, each building on the last or feeding back into a loop. The calculations themselves aren't particularly complex -- though they aren't the kind of math you'd want to do with a pen and paper.

To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough OOD sentences in an unbiased way is a laborious and time-consuming job. This paper proposes a novel neural sentence embedding method that represents sentences in a low-dimensional continuous vector space that emphasizes aspects that distinguish ID cases from OOD cases. We first used a large set of unlabeled text to pre-train word representations that are used to initialize neural sentence embedding. Then we used domain-category analysis as an auxiliary task to train neural sentence embedding for OOD sentence detection. After the sentence representations were learned, we used them to train an autoencoder aimed at OOD sentence detection. We evaluated our method by experimentally comparing it to the state-of-the-art methods in an eight-domain dialog system; our proposed method achieved the highest accuracy in all tests.

Latent truth discovery, LTD for short, refers to the problem of aggregating ltiple claims from various sources in order to estimate the plausibility of atements about entities. In the absence of a ground truth, this problem is highly challenging, when some sources provide conflicting claims and others no claims at all. In this work we provide an unsupervised stochastic inference procedure on top of a model that combines restricted Boltzmann machines with feed-forward neural networks to accurately infer the reliability of sources as well as the plausibility of statements about entities. In comparison to prior work our approach stands out (1) by allowing the incorporation of arbitrary features about sources and claims, (2) by generalizing from reliability per source towards a reliability function, and thus (3) enabling the estimation of source reliability even for sources that have provided no or very few claims, (4) by building on efficient and scalable stochastic inference algorithms, and (5) by outperforming the state-of-the-art by a considerable margin.