TensorFlow is an open source software library for numerical computation using data-flow graphs. It was originally developed by the Google Brain Team within Google's Machine Intelligence research organization for machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well. It reached version 1.0 in February 2017, and has continued rapid development, with 21,000 commits thus far, many from outside contributors. This article introduces TensorFlow, its open source community and ecosystem, and highlights some interesting TensorFlow open sourced models. It runs on nearly everything: GPUs and CPUs--including mobile and embedded platforms--and even tensor processing units (TPUs), which are specialized hardware to do tensor math on.

AI (artificial intelligence) will not confront human beings but serve as tools at their disopal, as human brain will remain the most powerful, although some say AI machines may be able to talk with people and judge their emotions in 2045 at the earliest, according to Aja Huang, one of the key developers behind AlphaGo, an AI program developed by Google's DeepMind unit. Huang made the comments when delivering a speech at the 2017 Taiwan AI Conference hosted recently by the Institute of Information Science under Academia Sinica and Taiwan Data Science Foundation. Huang recalled that he was invited to join London-based Deep Mind Technologies in late 2012, two years after he won the gold medal at the 15th Computer Olympiad in Kanazawa in 2010. In February 2014, DeepMind was acquired by Google, allowing the AI team to enjoy sufficient advanced hardware resources such as power TPU (tensor processing unit) and enabling them to work out the world's most powerful AI program AlphaGo, which has stunned the world by beating global top Go players. In March, 2016, AlphaGo beat Lee Sedol, a South Korean professional Go player in a five-game match, marking the first time a computer Go program has beaten a 9-dan professional without handicaps.

Today, a Chinese manufacturer and a venture backed by Bill Gates will announce plans to commercialize a microscope that uses deep learning algorithms to automatically identify and count malaria parasites in a blood smear within 20 minutes. AI-powered microscopes could speed up diagnosis and standardize detection of malaria at a time when the mosquito-borne disease kills almost half a million people per year. An experimental version of the AI-powered microscope has already shown that it can detect malaria parasites well enough to meet the highest World Health Organization microscopy standard, known as competence level 1. That rating means that it performs on par with well-trained microscopists, although the researchers note that some expert microscopists can still outperform the automated system. That previous research, presented at the International Conference on Computer Vision [pdf] in October, has inspired the Global Good Fund--a partnership between the company Intellectual Ventures and Bill Gates--and a Chinese microscope manufacturer called Motic to take the next big commercialization step.

Building highly non-linear and non-parametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task-specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this article, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrom kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pre-trained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques.

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map to replace softmax in the classification task. Inspired by this concept, we propose here a new adversarial modeling method by substituting the classification loss of discriminator with triplet loss. Theoretical proof based on IPM (Integral probability metric) demonstrates that such setting will help the generator converge to the given distribution theoretically under some conditions. Moreover, since triplet loss requires the generator to maximize distance within a class, we justify tripletGAN is also helpful to prevent mode collapse through both theory and experiment.

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs). We propose a simpler and novel update scheme to maintain orthogonal recurrent weight matrices without using complex valued matrices. This is done by parametrizing with a skew-symmetric matrix using the Cayley transform. Such a parametrization is unable to represent matrices with negative one eigenvalues, but this limitation is overcome by scaling the recurrent weight matrix by a diagonal matrix consisting of ones and negative ones. The proposed training scheme involves a straightforward gradient calculation and update step. In several experiments, the proposed scaled Cayley orthogonal recurrent neural network (scoRNN) achieves superior results with fewer trainable parameters than other unitary RNNs.

In this paper, we study deep signal representations that are invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel construction introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks with homogeneous activation functions, may enjoy the same stability. In particular, we study the norm of such models, which acts as a measure of complexity, controlling both stability and generalization.

Dell EMC announces new machine learning and deep learning solutions, continuing the company's work to bring high performance computing (HPC) and data analytics capabilities to mainstream enterprises worldwide. This enables organizations to take advantage of the convergence of HPC and data analytics and realize advancements in areas including fraud detection, image processing, financial investment analysis and personalized medicine. These new innovations represent the next step in the company's focus on democratizing HPC, optimizing data analytics with artificial intelligence (AI) technology innovations, and advancing both the HPC and AI communities. While AI techniques, such as machine learning and deep learning, are rapidly being deployed by many organizations across several industries, only a small number possess the expertise to design, deploy and manage such systems to use them effectively for rapidly gaining new insights. By leveraging Dell EMC's ecosystem of strong, curated partnerships and internal expertise in HPC and data analytics services, the company's new solutions offer customers the ability to harness the power of the massive amounts of their collected data, delivering faster, better and deeper business insights in real-time.

You are free to share this article under the Attribution 4.0 International license. A new system that uses artificial intelligence to find cracks captured in videos of nuclear reactors could help reduce accidents as well as maintenance costs, researchers report. "Regular inspection of nuclear power plant components is important to guarantee safe operations," says Mohammad R. Jahanshahi, an assistant professor in the Lyles School of Civil Engineering at Purdue University. "However, current practice is time-consuming, tedious, and subjective and involves human technicians reviewing inspection videos to identify cracks on reactors," Jahanshahi says. The fact that nuclear reactors are submerged in water to maintain cooling complicates the inspection process.

Artificial Intelligence has been a hot word across all industries lately. Think all the fuss around self-driving cars, Google's updated Assistant and the general talks of how conversational interfaces are the future of tech. Around 54 percent of retailers already use or plan to add artificial intelligence technology to their toolkit, with 20 percent planning to introduce some AI within the next 12 months, according to the latest report from SLI Systems. The increased adoption of AI in retail can be specifically attributed to advances in the deep learning. Deep learning is a specific machine learning approach to building and training neural networks.