Google LLC today launched an enterprise version of TensorFlow, the popular open-source artificial intelligence framework it created to run machine learning, deep learning and other statistical and predictive analytics workloads. Common use cases include training algorithms for image recognition and recurrent neural networks, as well as sequence-to-sequence models for machine translation and natural language processing. In a launch at the O'Reilly TensorFlow World conference in Santa Clara, California, Craig Wiley (pictured), director of product management at Google Cloud AI Platform, said the launch of TensorFlow Enterprise was necessary to meet the "higher demands and expectations" of enterprises that need to scale up their machine learning projects. TensorFlow Enterprise customers will be able to take advantage of what Google says is enterprise-grade support, including long-term support for older versions of the framework. Although TensorFlow is updated regularly, not everyone is able to upgrade to the newest releases immediately.

SC19 -- NVIDIA today announced the availability of a new kind of GPU-accelerated supercomputer in the cloud on Microsoft Azure. Built to handle the most demanding AI and high performance computing applications, the largest deployments of Azure's new NDv2 instance rank among the world's fastest supercomputers, offering up to 800 NVIDIA V100 Tensor Core GPUs interconnected on a single Mellanox InfiniBand backend network. It enables customers for the first time to rent an entire AI supercomputer on demand from their desk, and match the capabilities of large-scale, on-premises supercomputers that can take months to deploy. "Until now, access to supercomputers for AI and high performance computing has been reserved for the world's largest businesses and organizations," said Ian Buck, vice president and general manager of Accelerated Computing at NVIDIA. "Microsoft Azure's new offering democratizes AI, giving wide access to an essential tool needed to solve some of the world's biggest challenges."

Though machine learning has been around for more than three decades, it took a lot of time for the hardware to catch up with the demands of these power-hungry algorithms. With each passing year, the chip-set manufacturers have tried to make the hardware lighter and faster. Today, over 100 companies are working on building next-generation chips and hardware architectures that would match the capabilities of algorithms. These chips are capable of enabling deep learning applications on smartphones and other edge computing devices. Intel recently revealed new details of upcoming high-performance artificial intelligence accelerators: Intel Nervana neural network processors.

To view the code, training visualizations, and more information about the python example at the end of this post, visit the Comet project page. While much of the writing and literature on deep learning concerns computer vision and natural language processing (NLP), audio analysis -- a field that includes automatic speech recognition (ASR), digital signal processing, and music classification, tagging, and generation -- is a growing subdomain of deep learning applications. Some of the most popular and widespread machine learning systems, virtual assistants Alexa, Siri and Google Home, are largely products built atop models that can extract information from audio signals. Many of our users at Comet are working on audio related machine learning tasks such as audio classification, speech recognition and speech synthesis, so we built them tools to analyze, explore and understand audio data using Comet's meta machine-learning platform. This post is focused on showing how data scientists and AI practitioners can use Comet to apply machine learning and deep learning methods in the domain of audio analysis.

The IEEE Symposium on Security and Privacy (IEEE S&P) is one of the top-tier conferences in computer security and electronic privacy. This year, the IEEE S&P was held in May, in San Francisco. It was not a regular edition, as this flagship conference marked its 40th anniversary. This year's symposium was a special celebration that included a plenary session with some exceptional panelists from the S&P community, Test of Time awards for papers that have made a lasting impact on the field, and even an amazing birthday cake! I had the pleasure of presenting two research papers at two different workshops while at the conference: the Deep Learning and Security Workshop (DLS 2019) and the Workshop on Traffic Measurements for Cybersecurity (WTMC 2019). Both papers were based on my master's thesis, that I developed for the most part when I was a research intern at the Austrian Institute of Technology (AIT) in Vienna, Austria.

While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of large-scale fluid flow simulations of relevance to turbulence modeling and climate modeling. We adopt a hybrid approach by marrying two well-established turbulent flow simulation techniques with deep learning. Specifically, we introduce trainable spectral filters in a coupled model of Reynolds-averaged Navier-Stokes (RANS) and Large Eddy Simulation (LES), followed by a specialized U-net for prediction. Our approach, which we call turbulent-Flow Net (TF-Net), is grounded in a principled physics model, yet offers the flexibility of learned representations. We compare our model, TF-Net, with state-of-the-art baselines and observe significant reductions in error for predictions60frames ahead. Most importantly, our method predicts physical fields that obey desirable physical characteristics, such as conservation of mass, whilst faithfully emulating the turbulent kinetic energy field and spectrum, which are critical for accurate prediction of turbulent flows.

Cryo-electron microscopy (cryo-EM) is capable of producing reconstructed 3D images of biomolecules at near-atomic resolution. As such, it represents one of the most promising imaging techniques in structural biology. However, raw cryo-EM images are only highly corrupted - noisy and band-pass filtered - 2D projections of the target 3D biomolecules. Reconstructing the 3D molecular shape starts with the removal of image outliers, the estimation of the orientation of the biomolecule that has produced the given 2D image, and the estimation of camera parameters to correct for intensity defects. Current techniques performing these tasks are often computationally expensive, while the dataset sizes keep growing. There is a need for next-generation algorithms that preserve accuracy while improving speed and scalability. In this paper, we combine variational autoencoders (VAEs) and generative adversarial networks (GANs) to learn a low-dimensional latent representation of cryo-EM images. We perform an exploratory analysis of the obtained latent space, that is shown to have a structure of "orbits", in the sense of Lie group theory, consistent with the acquisition procedure of cryo-EM images. This analysis leads us to design an estimation method for orientation and camera parameters of single-particle cryo-EM images, together with an outliers detection procedure. As such, it opens the door to geometric approaches for unsupervised estimations of orientations and camera parameters, making possible fast cryo-EM biomolecule reconstruction.

It has been shown that using geometric spaces with non-zero curvature instead of plain Euclidean spaces with zero curvature improves performance on a range of Machine Learning tasks for learning representations. Recent work has leveraged these geometries to learn latent variable models like Variational Autoencoders (VAEs) in spherical and hyperbolic spaces with constant curvature. While these approaches work well on particular kinds of data that they were designed for e.g. tree-like data for a hyperbolic VAE, there exists no generic approach unifying all three models. We develop a Mixed-curvature Variational Autoencoder, an efficient way to train a VAE whose latent space is a product of constant curvature Riemannian manifolds, where the per-component curvature can be learned. This generalizes the Euclidean VAE to curved latent spaces, as the model essentially reduces to the Euclidean VAE if curvatures of all latent space components go to 0.

We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having the perception (pose, illumination and expression) fixed. We achieve this by a novel feed-forward encoder-decoder network architecture that is conditioned on the high-level representation of a person's facial image. The network is global, in the sense that it does not need to be retrained for a given video or for a given identity, and it creates natural looking image sequences with little distortion in time.

MNRAS 000, 1-7 (2019) Preprint 20 November 2019 Compiled using MNRAS L A T EX style file v3.0 Eliminating artefacts in Polarimetric Images using Deep Learning D. Paranjpye, 1 null A. Mahabal, 2 A.N. Ramaprakash, 3 G. Received YYY; in original form ZZZ ABSTRACT Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field polarimetry surveys, it is imperative to develop methods that automatically flag artefacts in images. In this paper, we implement a Convolutional Neural Network to identify the most dominant artefacts in the images. We find that our model can successfully classify sources with 98% true positive and 97% true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like W ALOP. Key words: deep learning - image classification - artefact detection - polarimetry 1 INTRODUCTION RoboPol (Ramaprakash et al. 2019) is a four-channel optical polarimeter installed on the 1.3m telescope at the Ski-nakas Observatory in Crete, Greece that is primarily used for polarimetry of point sources in the R band.