Learning K-way D-dimensional Discrete Code For Compact Embedding Representations

/in /by

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a “one-hot” encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary size and can lead to overfitting. In this work, we propose a much more compact K-way D-dimensional discrete encoding scheme to replace the “one-hot” encoding. In the proposed “KD encoding”, each symbol is represented by a D-dimensional code with a cardinality of K, and the final symbol embedding vector is generated by composing the code embedding vectors. To end-to-end learn semantically meaningful codes, we derive a relaxed discrete optimization approach based on stochastic gradient descent, which can be generally applied to any differentiable computational graph with an embedding layer. In our experiments with various applications from natural language processing to graph convolutional networks, the total size of the embedding layer can be reduced up to 98% while achieving similar or better performance.

Read more

LogLens: A Real-time Log Analysis System

/in /by

Administrators of most user-facing systems depend on periodic log data to get an idea of the health and status of production applications. Logs report information, which is crucial to diagnose the root cause of complex problems. In this paper, we present a real-time log analysis system called LogLens that automates the process of anomaly detection from logs with no (or minimal) target system knowledge and user specification. In LogLens, we employ unsupervised machine learning based techniques to discover patterns in application logs, and then leverage these patterns along with the real-time log parsing for designing advanced log analytics applications. Compared to the existing systems which are primarily limited to log indexing and search capabilities, LogLens presents an extensible system for supporting both stateless and stateful log analysis applications. Currently, LogLens is running at the core of a commercial log analysis solution handling millions of logs generated from the large-scale industrial environments and reported up to 12096x man-hours reduction in troubleshooting operational problems compared to the manual approach.

Read more

Spectrally Efficient Submarine Transmission with Flexible WME

/in /by

By adjusting single shaping factor in the distribution matcher, probabilistic-shaped M-QAM is reviewed to provide both flex-rate and near-Shannon performance at the given flex-grid bandwidth and filling ratio.

Read more

Attend and Interact: Higher-Order Object Interactions for Video Understanding

/in /by

Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation or pairwise object relationships. Furthermore, learning interactions across multiple objects in hundreds of frames for video is computationally infeasible and performance may suffer since a large combinatorial space has to be modeled. In this paper, we propose to efficiently learn higher-order interactions between arbitrary subgroups of objects for fine-grained video understanding. We demonstrate that modeling object interactions significantly improves accuracy for both action recognition and video captioning, while saving more than 3-times the computation over traditional pairwise relationships. The proposed method is validated on two large-scale datasets: Kinetics and ActivityNet Captions. Our SINet and SINet-Caption achieve state-of-the-art performances on both datasets even though the videos are sampled at a maximum of 1 FPS. To the best of our knowledge, this is the first work modeling object interactions on open domain large-scale video datasets, and we additionally model higher-order object interactions which improves the performance with low computational costs.

Read more

Fast and Accurate Online Video Object Segmentation via Tracking Parts

/in /by

Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

Read more

Learning to Adapt Structured Output Space for Semantic Segmentation

/in /by

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. To further improve our method, we utilize multi-level output adaptation based on feature maps at different levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.

Read more

Adaptive and Integared PV Output control with Battery Energy Storage

/in /by

An adaptive control system for battery integrated PV generation is designed to reduce the fluctuating in PV power production. The core component of the system is a four-layer power control system (PCS) for Battery Energy Storage (BES). BES responds to the power dispatch commands from PCS and charges/discharges to mitigate variations in PV power output. As a core part of the system, a novel PV power smoothing algorithm is proposed to reduce battery capacity requirements and reduce battery life losses by adaptively adjusting control parameter settings based on real-time system characteristics. Extensive simulation results based on real PV generation data have been presented to justify the effectiveness of the proposed approach and to show how several key parameters affect its performance.

Read more

Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

/in /by

Unsupervised anomaly detection on multi- or high-dimensional data is of great importance in both fundamental machine learning research and industrial applications, for which density estimation lies at the core. Although previous approaches based on dimensionality reduction followed by density estimation have made fruitful progress, they mainly suffer from decoupled model learning with inconsistent optimization goals and incapability of preserving essential information in the low-dimensional space. In this paper, we present a Deep Autoencoding Gaussian Mixture Model (DAGMM) for unsupervised anomaly detection. Our model utilizes a deep autoencoder to generate a low-dimensional representation and reconstruction error for each input data point, which is further fed into a Gaussian Mixture Model (GMM). Instead of using decoupled two-stage training and the standard Expectation-Maximization (EM) algorithm, DAGMM jointly optimizes the parameters of the deep autoencoder and the mixture model simultaneously in an end-to-end fashion, leveraging a separate estimation network to facilitate the parameter learning of the mixture model. The joint optimization, which well balances autoencoding reconstruction, density estimation of latent representation, and regularization, helps the autoencoder escape from less attractive local optima and further reduce reconstruction errors, avoiding the need of pre-training. Experimental results on several public benchmark datasets show that, DAGMM significantly outperforms state-of-the-art anomaly detection techniques, and achieves up to 14% improvement based on the standard F1 score.

Read more

Co-Regularized Deep Multi-Network Embedding

/in /by

Network embedding aims to learn a low-dimensional vector representation for each node in the social and information networks, with the constraint to preserve network structures. Most existing methods focus on single network embedding, ignoring the relationship between multiple networks. In many real-world applications, however, multiple networks may contain complementary information, which can lead to further refined node embeddings. Thus, in this paper, we propose a novel multi-network embedding method, DMNE. DMNE is flexible. It allows different networks to have different sizes, to be (un)weighted and (un)directed. It leverages multiple networks via cross-network relationships between nodes in different networks, which may form many-to-many node mappings, and be associated with weights. To model the non-linearity of the network data, we develop DMNE to have a new deep learning architecture, which coordinates multiple neural networks (one for each input network data) with a co-regularized loss function. With multiple layers of non-linear mappings, DMNE progressively transforms each input network to a highly non-linear latent space, and in the meantime, adapts different spaces to each other through a co-regularized learning schema. Extensive experimental results on real-life datasets demonstrate the effectiveness of our method.

Read more

Optimal Sizing and Operation of Energy Storage for Demand Charge Management and PV Utilization

/in /by

This paper presents a method to determine optimal energy and power capacity of distributed Energy Storage Systems (ESS) in behind-the-meter applications to maximize local Photovoltaic (PV) utilization or minimize Demand Charge (DC) cost. The problem is solved as a multi-objective optimization model to obtain a set of Pareto optimal solutions for each scenario in each month. An approach is then presented to map the monthly Pareto fronts into a single yearly Pareto front. A cost benefit analysis has also been carried out to show the compromise between PV utilization, DC cost, and ESS cost.

Read more