Entries by NEC Labs America

Conditional GAN with Discriminative Filter Generation for Text-to-Video Synthesis

/in /by

Developing conditional generative models for text-to-video synthesis is an extremely challenging yet an important topic of research in machine learning. In this work, we address this problem by introducing Text-Filter conditioning Generative Adversarial Network (TFGAN), a conditional GAN model with a novel multi-scale text-conditioning scheme that improves text-video associations. By combining the proposed conditioning scheme with a deep GAN architecture, TFGAN generates high quality videos from text on challenging real-world video datasets. In addition, we construct a synthetic dataset of text-conditioned moving shapes to systematically evaluate our conditioning scheme. Extensive experiments demonstrate that TFGAN significantly outperforms existing approaches, and can also generate videos of novel categories not seen during training.

A Study on Traffic Flow Monitoring Using Optical Fiber Sensor Technology

/in /by

Traffic conditions of the highway, Ya traffic volume meter CCTV Because it is observed in the spot, such as the discovery of traffic disturbances which deviates from the observation spot it may be delayed. The traffic flow has a problem from the point observations data indirectly order to be estimated, the capture accuracy of trending and regional circumstances change in time series. Therefore, we focused on the optical fiber sensing technology that utilizes the existing light off Aibainfura highway, actually measuring the travel vibration of the vehicle from the infrastructure as a continuous line, overhead grasp the traffic flow from the traveling locus We are working to. This time, tried traffic flow observation and the estimates of the average speed in the Tokyo, Nagoya and New Tomei Expressway. A result, the demonstration zone 45km in a traffic flow observable real time, succeeded in average speed calculation equivalent to the existing traffic meter, this technology has shown promise as a bird’s-eye technique wide and real-time traffic flow.

Deep Supervision with Intermediate Concepts (IEEE)

/in /by

Read Deep Supervision with Intermediate Concepts (IEEE). Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human and machine vision suggest that there are often intermediate representations that are intrinsic to an inference task, and which provide essential structure to improve generalization. In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice. We formulate a probabilistic framework which formalizes these notions and predicts improved generalization via this deep supervision method. One advantage of this approach is that we are able to train only from synthetic CAD renderings of cluttered scenes, where concept values can be extracted, but apply the results to real images. Our implementation achieves the state-of-the-art performance of 2D/3D keypoint localization and image classification on real image benchmarks including KITTI, PASCALVOC, PASCAL3D+, IKEA, and CIFAR100. We provide additional evidence that our approach outperforms alternative forms of supervision, such as multi-task networks.

Pose-variant 3D Facial Attribute Generation

/in /by

We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given by UV texture and position maps, resulting in photorealistic, geometrically-consistent and identity-preserving outputs. Starting from a self-occluded UV texture map obtained by applying an off-the-shelf 3D reconstruction method, we propose two novel components. First, a texture completion generative adversarial network (TC-GAN) completes the partial UV texture map. Second, a 3D attribute generation GAN (3DA-GAN) synthesizes the target attribute while obtaining an appearance consistent with 3D face geometry and preserving identity. Extensive experiments on CelebA, LFW and IJB-A show that our method achieves consistently better attribute generation accuracy than prior methods, a higher degree of qualitative photorealism and preserves face identity information.

Size and Alignment Independent Classification of the High-order Spatial Modes of a Light Beam Using a Convolutional Neural Network

/in /by

The higher-order spatial modes of a light beam are receiving significant interest. They can be used to further increase the data speeds of high speed optical communication, and for novel optical sensing modalities. As such, the classification of higher-order spatial modes is ubiquitous. Canonical classification methods typically require the use of unconventional optical devices. However, in addition to having prohibitive cost, complexity, and efficacy, such methods are dependent on the light beam’s size and alignment. In this work, a novel method to classify higher-order spatial modes is presented, where a convolutional neural network is applied to images of higher-order spatial modes that are taken with a conventional camera. In contrast to previous methods, by training the convolutional neural network with higher-order spatial modes of various alignments and sizes, this method is not dependent on the light beam’s size and alignment. As a proof of principle, images of 4 Hermite-Gaussian modes (HG00, HG01, HG10, and HG11) are numerically calculated via known solutions to the electromagnetic wave equation, and used to synthesize training examples. It is shown that as compared to training the convolutional neural network with training examples that have the same sizes and alignments, a?~2×?increase in accuracy can be achieved.

Field and lab experimental demonstration of nonlinear impairment compensation using neural networks

/in /by

Fiber nonlinearity is one of the major limitations to the achievable capacity in long distance fiber optic transmission systems. Nonlinear impairments are determined by the signal pattern and the transmission system parameters. Deterministic algorithms based on approximating the nonlinear Schrodinger equation through digital back propagation, or a single step approach based on perturbation methods have been demonstrated, however, their implementation demands excessive signal processing resources, and accurate knowledge of the transmission system. A completely different approach uses machine learning algorithms to learn from the received data itself to figure out the nonlinear impairment. In this work, a single-step, system agnostic nonlinearity compensation algorithm based on a neural network is proposed to pre-distort symbols at transmitter side to demonstrate ~0.6?dB Q improvement after 2800?km standard single-mode fiber transmission using 32 Gbaud signal. Without prior knowledge of the transmission system, the neural network tensor weights are constructed from training data thanks to the intra-channel cross-phase modulation and intra-channel four-wave mixing triplets used as input features.

Decentralized Transactive Energy Auctions with Bandit Learning

/in /by

The power systems worldwide have been embracing the rapid growth of distributed energy resources. Commonly, distributed energy resources exist in the distribution level, such as electric vehicles, rooftop photovoltaic panels, and home battery systems, which cannot be controlled by a centralized entity like a utility. However, a large number of distributed energy resources have potential to reshape the power generation landscape when the owners (prosumers) are allowed to send electricity back to the grids. Transactive energy paradigms are emerging for orchestrating the coordination of prosumers and consumers by enabling the exchange of energy among them. In this paper, we propose a transactive energy auction framework based on blockchain technology for creating trustworthy and transparent transactive environments in distribution networks, which does not rely on a centralized entity to clear transactions. Moreover, we propose intelligent decentralized decision-making strategies by bandit learning for market participants to locally decide their energy prices in auctions. The bandit learning approach can provide market participants with more benefits under the blockchain framework than trading energy with the centralized entity, which is further supported by the preliminary simulated results conducted over our blockchain-based platform.

Energy Predictive Models with Limited Data using Transfer Learning

/in /by

In this paper, we consider the problem of developing predictive models with limited data for energy assets such as electricity loads, PV power generations, etc. We specifically investigate the cases where the amount of historical data is not sufficient to effectively train the prediction model. We first develop an energy predictive model based on convolutional neural network (CNN) which is well suited to capture the interaday, daily, and weekly cyclostationary patterns, trends and seasonalities in energy assets time series. A transfer learning strategy is then proposed to address the challenge of limited training data. We demonstrate our approach on a usecase of daily electricity demand forecasting. we show practicing the transfer learning strategy on the CNN model results in significant improvement to existing forecasting methods.

Clairvoyant Networks

/in /by

We use the term clairvoyant to refer to networks that provide on-demand visibility for any flow at any time. Traditionally, network visibility is achieved by instrumenting and passively monitoring all flows in a network. SDN networks, by design endowed with full visibility, offer another alternative to network-wide flow monitoring. Both approaches incur significant capital and operational costs to make networks clairvoyant. In this paper, we argue that we can make any existing network clairvoyant by installing one or more SDN-enabled switches and a specialized controller to support on-demand visibility. We analyze the benefits and costs of such clairvoyant networks and provide a basic design by integrating two existing mechanisms for updating paths through legacy switches with SDN, telekinesis and magnet MACs. Our evaluation on a lab testbed and through extensive simulations show that, even with a single SDN-enabled switch, operators can make any flow visible for monitoring within milliseconds, albeit at 38% average increase in path length. With as many as 2% strategically chosen legacy switches replaced with SDN switches, clairvoyant networks achieve on-demand flow visibility with negligible overhead.