This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning purposes. We evaluate the positioning accuracy of state-of-the-art CNNs with channel fingerprints generated from a channel model with a rich clustered structure: the COST 2100 channel model. We find that moderately deep CNNs can achieve fractional-wavelength positioning accuracies, provided that an enough representative data set is available for training.

This study compares various superlearner and deep learning architectures (machine-learning-based and neural-network-based) for classification problems across several simulated and industrial datasets to assess performance and computational efficiency, as both methods have nice theoretical convergence properties. Superlearner formulations outperform other methods at small to moderate sample sizes (500-2500) on nonlinear and mixed linear/nonlinear predictor relationship datasets, while deep neural networks perform well on linear predictor relationship datasets of all sizes. This suggests faster convergence of the superlearner compared to deep neural network architectures on many messy classification problems for real-world data. Superlearners also yield interpretable models, allowing users to examine important signals in the data; in addition, they offer flexible formulation, where users can retain good performance with low-computational-cost base algorithms. K-nearest-neighbor (KNN) regression demonstrates improvements using the superlearner framework, as well; KNN superlearners consistently outperform deep architectures and KNN regression, suggesting that superlearners may be better able to capture local and global geometric features through utilizing a variety of algorithms to probe the data space.

As advancements in computing technologies and the expanding use of e-commerce platforms dramatically increase the risk of fraud for financial companies, many are turning to deep learning to better protect themselves and their customers.

"I learned very early the difference of knowing the name of something and knowing something." Terms like deep learning and neural networks get tossed around a lot lately but few people outside of Google and MIT can really explain simply what they are, how they work or why they're used. It's no wonder, deep learning gets into some pretty deep calculus. It also requires an enormous amount of data and seemingly endless amount of repetition. But machine learning is a fascinating concept.

This video, with the help of practical projects, highlights how TensorFlow can be used in different scenarios--this includes projects for training models, machine learning, deep learning, and working with various neural networks. Each project provides exciting and insightful exercises that will teach you how to use TensorFlow and show you how layers of data can be explored by working with tensors. Simply pick a project in line with your environment and get stacks of information on how to implement TensorFlow in production. Rodolfo Bonnin is a Systems Engineer and PhD student at Universidad Tecnológica Nacional, Argentina. He also pursued parallel programming and image understanding postgraduate courses at Uni Stuttgart, Germany.

AI is no longer a differentiator amongst startups, it has become a default feature that most firms will need to have as one of their core capabilities. UK has never been short of AI success stories, with one of the first being Deepmind, that was acquired by Google in 2014. The Fintech wave was just getting started then, and there have been some good tales in the UK-AI-Consumer Fintech space, across various sub-clusters. Cleo, an AI assistant that helps customers manage personal finance was founded in 2015, and after two years of work was launched commercially this year. The AI assistant taps into consumers' bank accounts and helps them save money.

Qualcomm Technologies (QCOM) announced that it has acquired machine learning startup Scyfer for an undisclosed amount. Scyfer B.V. is a startup that is affiliated with University of Amsterdam and focuses on applying machine learning techniques to different fields. Through the acquisition, Qualcomm hopes to further incorporate AI technology into different devices, including cars, machines and robotics. Netherlands-based Scyfer was founded in 2013 to provide AI for companies in industries such as manufacturing, healthcare and finance. Management was headed by Co-founder and CTO Tijmen Blankevoort, who was previously co-founder of Cyno Intelligent System.

Are you looking to gain in-depth knowledge of machine learning and deep learning? Packt's Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it. R is one of the leading technologies in the field of data science. Starting out at a basic level, this Learning Path will teach you how to develop and implement machine learning and deep learning algorithms using R in real-world scenarios. The Learning Path begins with covering some basic concepts of R to refresh your knowledge of R before we deep-dive into the advanced techniques.

The startup behind the Prisma style transfer app is shifting focus onto the b2b space, building tools for developers that draw on its expertise using neural networks and deep learning technology to power visual effects on mobile devices. It's launched a new website, Prismalabs.ai, detailing this new offering. Initially, say Prisma's co-founders, they'll be offering an SDK for developers wanting to add effects like style transfer and selfie lenses to their own apps -- likely launching an API mid next week. Then, in the "next month or so", they also plan to offer another service for developers wanting help to port their code to mobile. This was, after all, how the co-founders originally came up with the idea for the Prisma app -- having seen a style transfer effect working (slowly) on a desktop computer and realized how much potential it would have if it could be made to work in near real-time on mobile.

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improve Convolutional Neural Network (CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance.