July 28, 2019

3300 words 16 mins read

Paper Group ANR 451

Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision. Hand Gesture Real Time Paint Tool - Box. Matrix Completion via Factorizing Polynomials. Priming Neural Networks. Data-Intensive Supercomputing in the Cloud: Global Analytics for Satellite Imagery. LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vec …

Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision


Title	Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision
Authors	Amr Suleiman, Yu-Hsin Chen, Joel Emer, Vivienne Sze
Abstract	Computer vision enables a wide range of applications in robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. For many of these applications, local embedded processing is preferred due to privacy and/or latency concerns. Accordingly, energy-efficient embedded vision hardware delivering real-time and robust performance is crucial. While deep learning is gaining popularity in several computer vision algorithms, a significant energy consumption difference exists compared to traditional hand-crafted approaches. In this paper, we provide an in-depth analysis of the computation, energy and accuracy trade-offs between learned features such as deep Convolutional Neural Networks (CNN) and hand-crafted features such as Histogram of Oriented Gradients (HOG). This analysis is supported by measurements from two chips that implement these algorithms. Our goal is to understand the source of the energy discrepancy between the two approaches and to provide insight about the potential areas where CNNs can be improved and eventually approach the energy-efficiency of HOG while maintaining its outstanding performance accuracy.
Tasks	Self-Driving Cars
Published	2017-03-17
URL	http://arxiv.org/abs/1703.05853v1
PDF	http://arxiv.org/pdf/1703.05853v1.pdf
PWC	https://paperswithcode.com/paper/towards-closing-the-energy-gap-between-hog
Repo
Framework

Hand Gesture Real Time Paint Tool - Box


Title	Hand Gesture Real Time Paint Tool - Box
Authors	Vandit Gajjar, Viraj Mavani, Ayesha Gurnani
Abstract	With current development universally in computing, now a days user interaction approaches with mouse, keyboard, touch-pens etc. are not sufficient. Directly using of hands or hand gestures as an input device is a method to attract people with providing the applications, through Machine Learning and Computer Vision. Human-computer interaction application in which you can simply draw different shapes, fill the colors, moving the folder from one place to another place and rotating your image with rotating your hand gesture all this will be without touching your device only. In this paper Machine Learning based hand gestures recognition is presented, with the use of Computer Vision different types of gesture applications have been created.
Tasks
Published	2017-09-03
URL	http://arxiv.org/abs/1709.00727v3
PDF	http://arxiv.org/pdf/1709.00727v3.pdf
PWC	https://paperswithcode.com/paper/hand-gesture-real-time-paint-tool-box
Repo
Framework

Matrix Completion via Factorizing Polynomials


Title	Matrix Completion via Factorizing Polynomials
Authors	Vatsal Shah, Nikhil Rao, Weicong Ding
Abstract	Predicting unobserved entries of a partially observed matrix has found wide applicability in several areas, such as recommender systems, computational biology, and computer vision. Many scalable methods with rigorous theoretical guarantees have been developed for algorithms where the matrix is factored into low-rank components, and embeddings are learned for the row and column entities. While there has been recent research on incorporating explicit side information in the low-rank matrix factorization setting, often implicit information can be gleaned from the data, via higher-order interactions among entities. Such implicit information is especially useful in cases where the data is very sparse, as is often the case in real-world datasets. In this paper, we design a method to learn embeddings in the context of recommendation systems, using the observation that higher powers of a graph transition probability matrix encode the probability that a random walker will hit that node in a given number of steps. We develop a coordinate descent algorithm to solve the resulting optimization, that makes explicit computation of the higher order powers of the matrix redundant, preserving sparsity and making computations efficient. Experiments on several datasets show that our method, that can use higher order information, outperforms methods that only use explicitly available side information, those that use only second-order implicit information and in some cases, methods based on deep neural networks as well.
Tasks	Matrix Completion, Recommendation Systems
Published	2017-05-04
URL	http://arxiv.org/abs/1705.02047v3
PDF	http://arxiv.org/pdf/1705.02047v3.pdf
PWC	https://paperswithcode.com/paper/matrix-completion-via-factorizing-polynomials
Repo
Framework

Priming Neural Networks


Title	Priming Neural Networks
Authors	Amir Rosenfeld, Mahdi Biparva, John K. Tsotsos
Abstract	Visual priming is known to affect the human visual system to allow detection of scene elements, even those that may have been near unnoticeable before, such as the presence of camouflaged animals. This process has been shown to be an effect of top-down signaling in the visual system triggered by the said cue. In this paper, we propose a mechanism to mimic the process of priming in the context of object detection and segmentation. We view priming as having a modulatory, cue dependent effect on layers of features within a network. Our results show how such a process can be complementary to, and at times more effective than simple post-processing applied to the output of the network, notably so in cases where the object is hard to detect such as in severe noise. Moreover, we find the effects of priming are sometimes stronger when early visual layers are affected. Overall, our experiments confirm that top-down signals can go a long way in improving object detection and segmentation.
Tasks	Object Detection
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05918v2
PDF	http://arxiv.org/pdf/1711.05918v2.pdf
PWC	https://paperswithcode.com/paper/priming-neural-networks
Repo
Framework

Data-Intensive Supercomputing in the Cloud: Global Analytics for Satellite Imagery


Title	Data-Intensive Supercomputing in the Cloud: Global Analytics for Satellite Imagery
Authors	Michael S. Warren, Samuel W. Skillman, Rick Chartrand, Tim Kelton, Ryan Keisler, David Raleigh, Matthew Turk
Abstract	We present our experiences using cloud computing to support data-intensive analytics on satellite imagery for commercial applications. Drawing from our background in high-performance computing, we draw parallels between the early days of clustered computing systems and the current state of cloud computing and its potential to disrupt the HPC market. Using our own virtual file system layer on top of cloud remote object storage, we demonstrate aggregate read bandwidth of 230 gigabytes per second using 512 Google Compute Engine (GCE) nodes accessing a USA multi-region standard storage bucket. This figure is comparable to the best HPC storage systems in existence. We also present several of our application results, including the identification of field boundaries in Ukraine, and the generation of a global cloud-free base layer from Landsat imagery.
Tasks
Published	2017-02-13
URL	http://arxiv.org/abs/1702.03935v1
PDF	http://arxiv.org/pdf/1702.03935v1.pdf
PWC	https://paperswithcode.com/paper/data-intensive-supercomputing-in-the-cloud
Repo
Framework

LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations


Title	LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations
Authors	Jarvan Law, Hankz Hankui Zhuo, Junhua He, Erhu Rong
Abstract	Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value vector space, which have obtained high performance in NLP tasks. However, most of the existing models assume the result trained by one of them are perfect correct and used as prior knowledge for improving the other model. Some other models use the information trained from external large corpus to help improving smaller corpus. In this paper, we aim to build such an algorithm framework that makes topic models and vector representations mutually improve each other within the same corpus. An EM-style algorithm framework is employed to iteratively optimize both topic model and vector representations. Experimental results show that our model outperforms state-of-art methods on various NLP tasks.
Tasks	Topic Models, Word Embeddings
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07117v1
PDF	http://arxiv.org/pdf/1702.07117v1.pdf
PWC	https://paperswithcode.com/paper/ltsg-latent-topical-skip-gram-for-mutually
Repo
Framework

Scalable Inference for Nested Chinese Restaurant Process Topic Models


Title	Scalable Inference for Nested Chinese Restaurant Process Topic Models
Authors	Jianfei Chen, Jun Zhu, Jie Lu, Shixia Liu
Abstract	Nested Chinese Restaurant Process (nCRP) topic models are powerful nonparametric Bayesian methods to extract a topic hierarchy from a given text corpus, where the hierarchical structure is automatically determined by the data. Hierarchical Latent Dirichlet Allocation (hLDA) is a popular instance of nCRP topic models. However, hLDA has only been evaluated at small scale, because the existing collapsed Gibbs sampling and instantiated weight variational inference algorithms either are not scalable or sacrifice inference quality with mean-field assumptions. Moreover, an efficient distributed implementation of the data structures, such as dynamically growing count matrices and trees, is challenging. In this paper, we propose a novel partially collapsed Gibbs sampling (PCGS) algorithm, which combines the advantages of collapsed and instantiated weight algorithms to achieve good scalability as well as high model quality. An initialization strategy is presented to further improve the model quality. Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy. Empirical studies show that our algorithm is 111 times more efficient than the previous open-source implementation for hLDA, with comparable or even better model quality. Our distributed implementation can extract 1,722 topics from a 131-million-document corpus with 28 billion tokens, which is 4-5 orders of magnitude larger than the previous largest corpus, with 50 machines in 7 hours.
Tasks	Topic Models
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07083v1
PDF	http://arxiv.org/pdf/1702.07083v1.pdf
PWC	https://paperswithcode.com/paper/scalable-inference-for-nested-chinese
Repo
Framework

Machine learning based compact photonic structure design for strong light confinement


Title	Machine learning based compact photonic structure design for strong light confinement
Authors	Mirbek Turduev, Çağrı Latifoğlu, İbrahim Halil Giden, Y. Sinan Hanay
Abstract	We present a novel approach based on machine learning for designing photonic structures. In particular, we focus on strong light confinement that allows the design of an efficient free-space-to-waveguide coupler which is made of Si- slab overlying on the top of silica substrate. The learning algorithm is implemented using bitwise square Si- cells and the whole optimized device has a footprint of $\boldsymbol{2 , \mu m \times 1, \mu m}$, which is the smallest size ever achieved numerically. To find the effect of Si- slab thickness on the sub-wavelength focusing and strong coupling characteristics of optimized photonic structure, we carried out three-dimensional time-domain numerical calculations. Corresponding optimum values of full width at half maximum and coupling efficiency were calculated as $\boldsymbol{0.158 \lambda}$ and $\boldsymbol{-1.87,dB}$ with slab thickness of $\boldsymbol{280nm}$. Compared to the conventional counterparts, the optimized lens and coupler designs are easy-to-fabricate via optical lithography techniques, quite compact, and can operate at telecommunication wavelengths. The outcomes of the presented study show that machine learning can be beneficial for efficient photonic designs in various potential applications such as polarization-division, beam manipulation and optical interconnects.
Tasks
Published	2017-01-31
URL	http://arxiv.org/abs/1702.00260v1
PDF	http://arxiv.org/pdf/1702.00260v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-compact-photonic
Repo
Framework

Generative Adversarial Network based on Resnet for Conditional Image Restoration


Title	Generative Adversarial Network based on Resnet for Conditional Image Restoration
Authors	Meng Wang, Huafeng Li, Fang Li
Abstract	The GANs promote an adversarive game to approximate complex and jointed example probability. The networks driven by noise generate fake examples to approximate realistic data distributions. Later the conditional GAN merges prior-conditions as input in order to transfer attribute vectors to the corresponding data. However, the CGAN is not designed to deal with the high dimension conditions since indirect guide of the learning is inefficiency. In this paper, we proposed a network ResGAN to generate fine images in terms of extremely degenerated images. The coarse images aligned to attributes are embedded as the generator inputs and classifier labels. In generative network, a straight path similar to the Resnet is cohered to directly transfer the coarse images to the higher layers. And adversarial training is circularly implemented to prevent degeneration of the generated images. Experimental results of applying the ResGAN to datasets MNIST, CIFAR10/100 and CELEBA show its higher accuracy to the state-of-art GANs.
Tasks	Image Restoration
Published	2017-07-16
URL	http://arxiv.org/abs/1707.04881v1
PDF	http://arxiv.org/pdf/1707.04881v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-network-based-on
Repo
Framework

Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation


Title	Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation
Authors	Zhaohan Daniel Guo, Philip S. Thomas, Emma Brunskill
Abstract	Evaluating a policy by deploying it in the real world can be risky and costly. Off-policy policy evaluation (OPE) algorithms use historical data collected from running a previous policy to evaluate a new policy, which provides a means for evaluating a policy without requiring it to ever be deployed. Importance sampling is a popular OPE method because it is robust to partial observability and works with continuous states and actions. However, the amount of historical data required by importance sampling can scale exponentially with the horizon of the problem: the number of sequential decisions that are made. We propose using policies over temporally extended actions, called options, and show that combining these policies with importance sampling can significantly improve performance for long-horizon problems. In addition, we can take advantage of special cases that arise due to options-based policies to further improve the performance of importance sampling. We further generalize these special cases to a general covariance testing rule that can be used to decide which weights to drop in an IS estimate, and derive a new IS algorithm called Incremental Importance Sampling that can provide significantly more accurate estimates for a broad class of domains.
Tasks
Published	2017-03-09
URL	http://arxiv.org/abs/1703.03453v2
PDF	http://arxiv.org/pdf/1703.03453v2.pdf
PWC	https://paperswithcode.com/paper/using-options-and-covariance-testing-for-long
Repo
Framework

Learning Geometric Concepts with Nasty Noise


Title	Learning Geometric Concepts with Nasty Noise
Authors	Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
Abstract	We study the efficient learnability of geometric concept classes - specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces - when a fraction of the data is adversarially corrupted. We give the first polynomial-time PAC learning algorithms for these concept classes with dimension-independent error guarantees in the presence of nasty noise under the Gaussian distribution. In the nasty noise model, an omniscient adversary can arbitrarily corrupt a small fraction of both the unlabeled data points and their labels. This model generalizes well-studied noise models, including the malicious noise model and the agnostic (adversarial label noise) model. Prior to our work, the only concept class for which efficient malicious learning algorithms were known was the class of origin-centered halfspaces. Specifically, our robust learning algorithm for low-degree PTFs succeeds under a number of tame distributions – including the Gaussian distribution and, more generally, any log-concave distribution with (approximately) known low-degree moments. For LTFs under the Gaussian distribution, we give a polynomial-time algorithm that achieves error $O(\epsilon)$, where $\epsilon$ is the noise rate. At the core of our PAC learning results is an efficient algorithm to approximate the low-degree Chow-parameters of any bounded function in the presence of nasty noise. To achieve this, we employ an iterative spectral method for outlier detection and removal, inspired by recent work in robust unsupervised learning. Our aforementioned algorithm succeeds for a range of distributions satisfying mild concentration bounds and moment assumptions. The correctness of our robust learning algorithm for intersections of halfspaces makes essential use of a novel robust inverse independence lemma that may be of broader interest.
Tasks	Outlier Detection
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01242v1
PDF	http://arxiv.org/pdf/1707.01242v1.pdf
PWC	https://paperswithcode.com/paper/learning-geometric-concepts-with-nasty-noise
Repo
Framework

The Kernel Mixture Network: A Nonparametric Method for Conditional Density Estimation of Continuous Random Variables


Title	The Kernel Mixture Network: A Nonparametric Method for Conditional Density Estimation of Continuous Random Variables
Authors	Luca Ambrogioni, Umut Güçlü, Marcel A. J. van Gerven, Eric Maris
Abstract	This paper introduces the kernel mixture network, a new method for nonparametric estimation of conditional probability densities using neural networks. We model arbitrarily complex conditional densities as linear combinations of a family of kernel functions centered at a subset of training points. The weights are determined by the outer layer of a deep neural network, trained by minimizing the negative log likelihood. This generalizes the popular quantized softmax approach, which can be seen as a kernel mixture network with square and non-overlapping kernels. We test the performance of our method on two important applications, namely Bayesian filtering and generative modeling. In the Bayesian filtering example, we show that the method can be used to filter complex nonlinear and non-Gaussian signals defined on manifolds. The resulting kernel mixture network filter outperforms both the quantized softmax filter and the extended Kalman filter in terms of model likelihood. Finally, our experiments on generative models show that, given the same architecture, the kernel mixture network leads to higher test set likelihood, less overfitting and more diversified and realistic generated samples than the quantized softmax approach.
Tasks	Density Estimation
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07111v1
PDF	http://arxiv.org/pdf/1705.07111v1.pdf
PWC	https://paperswithcode.com/paper/the-kernel-mixture-network-a-nonparametric
Repo
Framework

Towards Deep Learning Models for Psychological State Prediction using Smartphone Data: Challenges and Opportunities


Title	Towards Deep Learning Models for Psychological State Prediction using Smartphone Data: Challenges and Opportunities
Authors	Gatis Mikelsons, Matthew Smith, Abhinav Mehrotra, Mirco Musolesi
Abstract	There is an increasing interest in exploiting mobile sensing technologies and machine learning techniques for mental health monitoring and intervention. Researchers have effectively used contextual information, such as mobility, communication and mobile phone usage patterns for quantifying individuals’ mood and wellbeing. In this paper, we investigate the effectiveness of neural network models for predicting users’ level of stress by using the location information collected by smartphones. We characterize the mobility patterns of individuals using the GPS metrics presented in the literature and employ these metrics as input to the network. We evaluate our approach on the open-source StudentLife dataset. Moreover, we discuss the challenges and trade-offs involved in building machine learning models for digital mental health and highlight potential future work in this direction.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06350v1
PDF	http://arxiv.org/pdf/1711.06350v1.pdf
PWC	https://paperswithcode.com/paper/towards-deep-learning-models-for
Repo
Framework

A Robust Learning Algorithm for Regression Models Using Distributionally Robust Optimization under the Wasserstein Metric


Title	A Robust Learning Algorithm for Regression Models Using Distributionally Robust Optimization under the Wasserstein Metric
Authors	Ruidi Chen, Ioannis Ch. Paschalidis
Abstract	We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our approach mitigates the impact of outliers through hedging against a family of distributions on the observed data, some of which assign very low probabilities to the outliers. The set of distributions under consideration are close to the empirical distribution in the sense of the Wasserstein metric. We show that this DRO formulation can be relaxed to a convex optimization problem which encompasses a class of models. By selecting proper norm spaces for the Wasserstein metric, we are able to recover several commonly used regularized regression models. We provide new insights into the regularization term and give guidance on the selection of the regularization coefficient from the standpoint of a confidence region. We establish two types of performance guarantees for the solution to our formulation under mild conditions. One is related to its out-of-sample behavior (prediction bias), and the other concerns the discrepancy between the estimated and true regression planes (estimation bias). Extensive numerical results demonstrate the superiority of our approach to a host of regression models, in terms of the prediction and estimation accuracies. We also consider the application of our robust learning procedure to outlier detection, and show that our approach achieves a much higher AUC (Area Under the ROC Curve) than M-estimation.
Tasks	Outlier Detection
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02412v2
PDF	http://arxiv.org/pdf/1706.02412v2.pdf
PWC	https://paperswithcode.com/paper/a-robust-learning-algorithm-for-regression
Repo
Framework

Poisson multi-Bernoulli mixture filter: direct derivation and implementation


Title	Poisson multi-Bernoulli mixture filter: direct derivation and implementation
Authors	Ángel F. García-Fernández, Jason L. Williams, Karl Granström, Lennart Svensson
Abstract	We provide a derivation of the Poisson multi-Bernoulli mixture (PMBM) filter for multi-target tracking with the standard point target measurements without using probability generating functionals or functional derivatives. We also establish the connection with the \delta-generalised labelled multi-Bernoulli (\delta-GLMB) filter, showing that a \delta-GLMB density represents a multi-Bernoulli mixture with labelled targets so it can be seen as a special case of PMBM. In addition, we propose an implementation for linear/Gaussian dynamic and measurement models and how to efficiently obtain typical estimators in the literature from the PMBM. The PMBM filter is shown to outperform other filters in the literature in a challenging scenario.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04264v4
PDF	http://arxiv.org/pdf/1703.04264v4.pdf
PWC	https://paperswithcode.com/paper/poisson-multi-bernoulli-mixture-filter-direct
Repo
Framework