July 28, 2019

3323 words 16 mins read

Paper Group ANR 170

Real-Time Bidding by Reinforcement Learning in Display Advertising. ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network. A Survey of Distant Supervision Methods using PGMs. Reduced Electron Exposure for Energy-Dispersive Spectroscopy using Dynamic Sampling. Spatially-Adaptive Filter Units for Deep …

Real-Time Bidding by Reinforcement Learning in Display Advertising


Title	Real-Time Bidding by Reinforcement Learning in Display Advertising
Authors	Han Cai, Kan Ren, Weinan Zhang, Kleanthis Malialis, Jun Wang, Yong Yu, Defeng Guo
Abstract	The majority of online display ads are served through real-time bidding (RTB) — each ad display impression is auctioned off in real-time when it is just being generated from a user visit. To place an ad automatically and optimally, it is critical for advertisers to devise a learning algorithm to cleverly bid an ad impression in real-time. Most previous works consider the bid decision as a static optimization problem of either treating the value of each impression independently or setting a bid price to each segment of ad volume. However, the bidding for a given ad campaign would repeatedly happen during its life span before the budget runs out. As such, each bid is strategically correlated by the constrained budget and the overall effectiveness of the campaign (e.g., the rewards from generated clicks), which is only observed after the campaign has completed. Thus, it is of great interest to devise an optimal bidding strategy sequentially so that the campaign budget can be dynamically allocated across all the available impressions on the basis of both the immediate and future rewards. In this paper, we formulate the bid decision process as a reinforcement learning problem, where the state space is represented by the auction information and the campaign’s real-time parameters, while an action is the bid price to set. By modeling the state transition via auction competition, we build a Markov Decision Process framework for learning the optimal bidding policy to optimize the advertising performance in the dynamic real-time bidding environment. Furthermore, the scalability problem from the large real-world auction volume and campaign budget is well handled by state value approximation using neural networks.
Tasks
Published	2017-01-10
URL	http://arxiv.org/abs/1701.02490v2
PDF	http://arxiv.org/pdf/1701.02490v2.pdf
PWC	https://paperswithcode.com/paper/real-time-bidding-by-reinforcement-learning
Repo
Framework

ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network


Title	ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network
Authors	Chaoyun Zhang, Xi Ouyang, Paul Patras
Abstract	Large-scale mobile traffic analytics is becoming essential to digital infrastructure provisioning, public transportation, events planning, and other domains. Monitoring city-wide mobile traffic is however a complex and costly process that relies on dedicated probes. Some of these probes have limited precision or coverage, others gather tens of gigabytes of logs daily, which independently offer limited insights. Extracting fine-grained patterns involves expensive spatial aggregation of measurements, storage, and post-processing. In this paper, we propose a mobile traffic super-resolution technique that overcomes these problems by inferring narrowly localised traffic consumption from coarse measurements. We draw inspiration from image processing and design a deep-learning architecture tailored to mobile networking, which combines Zipper Network (ZipNet) and Generative Adversarial neural Network (GAN) models. This enables to uniquely capture spatio-temporal relations between traffic volume snapshots routinely monitored over broad coverage areas (`low-resolution') and the corresponding consumption at 0.05 km $^2$ level (`high-resolution’) usually obtained after intensive computation. Experiments we conduct with a real-world data set demonstrate that the proposed ZipNet(-GAN) infers traffic consumption with remarkable accuracy and up to 100$\times$ higher granularity as compared to standard probing, while outperforming existing data interpolation techniques. To our knowledge, this is the first time super-resolution concepts are applied to large-scale mobile traffic analysis and our solution is the first to infer fine-grained urban traffic patterns from coarse aggregates.
Tasks	Super-Resolution
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02413v1
PDF	http://arxiv.org/pdf/1711.02413v1.pdf
PWC	https://paperswithcode.com/paper/zipnet-gan-inferring-fine-grained-mobile
Repo
Framework

A Survey of Distant Supervision Methods using PGMs


Title	A Survey of Distant Supervision Methods using PGMs
Authors	Gagan Madan
Abstract	Relation Extraction refers to the task of populating a database with tuples of the form $r(e_1, e_2)$, where $r$ is a relation and $e_1$, $e_2$ are entities. Distant supervision is one such technique which tries to automatically generate training examples based on an existing KB such as Freebase. This paper is a survey of some of the techniques in distant supervision which primarily rely on Probabilistic Graphical Models (PGMs).
Tasks	Relation Extraction
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03751v1
PDF	http://arxiv.org/pdf/1705.03751v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-distant-supervision-methods-using
Repo
Framework

Reduced Electron Exposure for Energy-Dispersive Spectroscopy using Dynamic Sampling


Title	Reduced Electron Exposure for Energy-Dispersive Spectroscopy using Dynamic Sampling
Authors	Yan Zhang, G. M. Dilshan Godaliyadda, Nicola Ferrier, Emine B. Gulsoy, Charles A. Bouman, Charudatta Phatak
Abstract	Analytical electron microscopy and spectroscopy of biological specimens, polymers, and other beam sensitive materials has been a challenging area due to irradiation damage. There is a pressing need to develop novel imaging and spectroscopic imaging methods that will minimize such sample damage as well as reduce the data acquisition time. The latter is useful for high-throughput analysis of materials structure and chemistry. In this work, we present a novel machine learning based method for dynamic sparse sampling of EDS data using a scanning electron microscope. Our method, based on the supervised learning approach for dynamic sampling algorithm and neural networks based classification of EDS data, allows a dramatic reduction in the total sampling of up to 90%, while maintaining the fidelity of the reconstructed elemental maps and spectroscopic data. We believe this approach will enable imaging and elemental mapping of materials that would otherwise be inaccessible to these analysis techniques.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1707.03848v1
PDF	http://arxiv.org/pdf/1707.03848v1.pdf
PWC	https://paperswithcode.com/paper/reduced-electron-exposure-for-energy
Repo
Framework

Spatially-Adaptive Filter Units for Deep Neural Networks


Title	Spatially-Adaptive Filter Units for Deep Neural Networks
Authors	Domen Tabernik, Matej Kristan, Aleš Leonardis
Abstract	Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters. In this paper we propose a novel displaced aggregation unit (DAU) that does not require hand-crafting. In contrast to classical filters with units (pixels) placed on a fixed regular grid, the displacement of the DAUs are learned, which enables filters to spatially-adapt their receptive field to a given problem. We extensively demonstrate the strength of DAUs on a classification and semantic segmentation tasks. Compared to ConvNets with regular filter, ConvNets with DAUs achieve comparable performance at faster convergence and up to 3-times reduction in parameters. Furthermore, DAUs allow us to study deep networks from novel perspectives. We study spatial distributions of DAU filters and analyze the number of parameters allocated for spatial coverage in a filter.
Tasks	Semantic Segmentation
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11473v2
PDF	http://arxiv.org/pdf/1711.11473v2.pdf
PWC	https://paperswithcode.com/paper/spatially-adaptive-filter-units-for-deep
Repo
Framework

Particle Value Functions


Title	Particle Value Functions
Authors	Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh
Abstract	The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control literature, we review the risk-sensitive value function that arises from an exponential utility and illustrate its effects on an example. This risk-sensitive value function is not always applicable to reinforcement learning problems, so we introduce the particle value function defined by a particle filter over the distributions of an agent’s experience, which bounds the risk-sensitive one. We illustrate the benefit of the policy gradients of this objective in Cliffworld.
Tasks
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05820v1
PDF	http://arxiv.org/pdf/1703.05820v1.pdf
PWC	https://paperswithcode.com/paper/particle-value-functions
Repo
Framework

Toward Cognitive and Immersive Systems: Experiments in a Cognitive Microworld


Title	Toward Cognitive and Immersive Systems: Experiments in a Cognitive Microworld
Authors	Matthew Peveler, Naveen Sundar Govindarajulu, Selmer Bringsjord, Biplav Srivastava, Kartik Talamadupula, Hui Su
Abstract	As computational power has continued to increase, and sensors have become more accurate, the corresponding advent of systems that are at once cognitive and immersive has arrived. These \textit{cognitive and immersive systems} (CAISs) fall squarely into the intersection of AI with HCI/HRI: such systems interact with and assist the human agents that enter them, in no small part because such systems are infused with AI able to understand and reason about these humans and their knowledge, beliefs, goals, communications, plans, etc. We herein explain our approach to engineering CAISs. We emphasize the capacity of a CAIS to develop and reason over a theory of the mind' of its human partners. This capacity entails that the AI in question has a sophisticated model of the beliefs, knowledge, goals, desires, emotions, etc.\ of these humans. To accomplish this engineering, a formal framework of very high expressivity is needed. In our case, this framework is a \textit{cognitive event calculus}, a particular kind of quantified multi-operator modal logic, and a matching high-expressivity automated reasoner and planner. To explain, advance, and to a degree validate our approach, we show that a calculus of this type satisfies a set of formal requirements, and can enable a CAIS to understand a psychologically tricky scenario couched in what we call the \textit{cognitive polysolid framework} (CPF). We also formally show that a room that satisfies these requirements can have a useful property we term \emph{expectation of usefulness}. CPF, a sub-class of \textit{cognitive microworlds}, includes machinery able to represent and plan over not merely blocks and actions (such as seen in the primitive blocks worlds’ of old), but also over agents and their mental attitudes about both other agents and inanimate objects.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.05958v2
PDF	http://arxiv.org/pdf/1709.05958v2.pdf
PWC	https://paperswithcode.com/paper/toward-cognitive-and-immersive-systems
Repo
Framework

Learning to see people like people


Title	Learning to see people like people
Authors	Amanda Song, Linjie Li, Chad Atalla, Garrison Cottrell
Abstract	Humans make complex inferences on faces, ranging from objective properties (gender, ethnicity, expression, age, identity, etc) to subjective judgments (facial attractiveness, trustworthiness, sociability, friendliness, etc). While the objective aspects of face perception have been extensively studied, relatively fewer computational models have been developed for the social impressions of faces. Bridging this gap, we develop a method to predict human impressions of faces in 40 subjective social dimensions, using deep representations from state-of-the-art neural networks. We find that model performance grows as the human consensus on a face trait increases, and that model predictions outperform human groups in correlation with human averages. This illustrates the learnability of subjective social perception of faces, especially when there is high human consensus. Our system can be used to decide which photographs from a personal collection will make the best impression. The results are significant for the field of social robotics, demonstrating that robots can learn the subjective judgments defining the underlying fabric of human interaction.
Tasks
Published	2017-05-05
URL	http://arxiv.org/abs/1705.04282v1
PDF	http://arxiv.org/pdf/1705.04282v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-see-people-like-people
Repo
Framework

Detection of Inferior Myocardial Infarction using Shallow Convolutional Neural Networks


Title	Detection of Inferior Myocardial Infarction using Shallow Convolutional Neural Networks
Authors	Tahsin Reasat, Celia Shahnaz
Abstract	Myocardial Infarction is one of the leading causes of death worldwide. This paper presents a Convolutional Neural Network (CNN) architecture which takes raw Electrocardiography (ECG) signal from lead II, III and AVF and differentiates between inferior myocardial infarction (IMI) and healthy signals. The performance of the model is evaluated on IMI and healthy signals obtained from Physikalisch-Technische Bundesanstalt (PTB) database. A subject-oriented approach is taken to comprehend the generalization capability of the model and compared with the current state of the art. In a subject-oriented approach, the network is tested on one patient and trained on rest of the patients. Our model achieved a superior metrics scores (accuracy= 84.54%, sensitivity= 85.33% and specificity= 84.09%) when compared to the benchmark. We also analyzed the discriminating strength of the features extracted by the convolutional layers by means of geometric separability index and euclidean distance and compared it with the benchmark model.
Tasks	Electrocardiography (ECG)
Published	2017-10-03
URL	http://arxiv.org/abs/1710.01115v4
PDF	http://arxiv.org/pdf/1710.01115v4.pdf
PWC	https://paperswithcode.com/paper/detection-of-inferior-myocardial-infarction
Repo
Framework

Sentiment Analysis by Joint Learning of Word Embeddings and Classifier


Title	Sentiment Analysis by Joint Learning of Word Embeddings and Classifier
Authors	Prathusha Kameswara Sarma, Bill Sethares
Abstract	Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings learn vector representations from large corpora of text documents in an unsu- pervised fashion. This paper introduces SWESA (Supervised Word Embeddings for Sentiment Analysis), an algorithm for sentiment analysis via word embeddings. SWESA leverages document label infor- mation to learn vector representations of words from a modest corpus of text doc- uments by solving an optimization prob- lem that minimizes a cost function with respect to both word embeddings as well as classification accuracy. Analysis re- veals that SWESA provides an efficient way of estimating the dimension of the word embeddings that are to be learned. Experiments on several real world data sets show that SWESA has superior per- formance when compared to previously suggested approaches to word embeddings and sentiment analysis tasks.
Tasks	Learning Word Embeddings, Sentiment Analysis, Word Embeddings
Published	2017-08-14
URL	http://arxiv.org/abs/1708.03995v1
PDF	http://arxiv.org/pdf/1708.03995v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-by-joint-learning-of-word
Repo
Framework

Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression


Title	Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression
Authors	Samet Oymak, Mehrdad Mahdavi, Jiasi Chen
Abstract	For various applications, the relations between the dependent and independent variables are highly nonlinear. Consequently, for large scale complex problems, neural networks and regression trees are commonly preferred over linear models such as Lasso. This work proposes learning the feature nonlinearities by binning feature values and finding the best fit in each quantile using non-convex regularized linear regression. The algorithm first captures the dependence between neighboring quantiles by enforcing smoothness via piecewise-constant/linear approximation and then selects a sparse subset of good features. We prove that the proposed algorithm is statistically and computationally efficient. In particular, it achieves linear rate of convergence while requiring near-minimal number of samples. Evaluations on synthetic and real datasets demonstrate that algorithm is competitive with current state-of-the-art and accurately learns feature nonlinearities. Finally, we explore an interesting connection between the binning stage of our algorithm and sparse Johnson-Lindenstrauss matrices.
Tasks
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07256v1
PDF	http://arxiv.org/pdf/1705.07256v1.pdf
PWC	https://paperswithcode.com/paper/learning-feature-nonlinearities-with-non
Repo
Framework

Superposed Episodic and Semantic Memory via Sparse Distributed Representation


Title	Superposed Episodic and Semantic Memory via Sparse Distributed Representation
Authors	Rod Rinkus, Jasmin Leveille
Abstract	The abilities to perceive, learn, and use generalities, similarities, classes, i.e., semantic memory (SM), is central to cognition. Machine learning (ML), neural network, and AI research has been primarily driven by tasks requiring such abilities. However, another central facet of cognition, single-trial formation of permanent memories of experiences, i.e., episodic memory (EM), has had relatively little focus. Only recently has EM-like functionality been added to Deep Learning (DL) models, e.g., Neural Turing Machine, Memory Networks. However, in these cases: a) EM is implemented as a separate module, which entails substantial data movement (and so, time and power) between the DL net itself and EM; and b) individual items are stored localistically within the EM, precluding realizing the exponential representational efficiency of distributed over localist coding. We describe Sparsey, an unsupervised, hierarchical, spatial/spatiotemporal associative memory model differing fundamentally from mainstream ML models, most crucially, in its use of sparse distributed representations (SDRs), or, cell assemblies, which admits an extremely efficient, single-trial learning algorithm that maps input similarity into code space similarity (measured as intersection). SDRs of individual inputs are stored in superposition and because similarity is preserved, the patterns of intersections over the assigned codes reflect the similarity, i.e., statistical, structure, of all orders, not simply pairwise, over the inputs. Thus, SM, i.e., a generative model, is built as a computationally free side effect of the act of storing episodic memory traces of individual inputs, either spatial patterns or sequences. We report initial results on MNIST and on the Weizmann video event recognition benchmarks. While we have not yet attained SOTA class accuracy, learning takes only minutes on a single CPU.
Tasks
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07829v1
PDF	http://arxiv.org/pdf/1710.07829v1.pdf
PWC	https://paperswithcode.com/paper/superposed-episodic-and-semantic-memory-via
Repo
Framework

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images


Title	Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images
Authors	Hongkai Wang, Zongwei Zhou, Yingci Li, Zhonghua Chen, Peiou Lu, Wenzhi Wang, Wanyu Liu, Lijuan Yu
Abstract	The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.
Tasks
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02223v1
PDF	http://arxiv.org/pdf/1702.02223v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-machine-learning-methods-for
Repo
Framework

Single Image Super-Resolution Using Lightweight CNN with Maxout Units


Title	Single Image Super-Resolution Using Lightweight CNN with Maxout Units
Authors	Jae-Seok Choi, Munchurl Kim
Abstract	Rectified linear units (ReLU) are well-known to be helpful in obtaining faster convergence and thus higher performance for many deep-learning-based applications. However, networks with ReLU tend to perform poorly when the number of filter parameters is constrained to a small number. To overcome it, in this paper, we propose a novel network utilizing maxout units (MU), and show its effectiveness on super-resolution (SR) applications. In general, the MU has been known to make the filter sizes doubled in generating the feature maps of the same sizes in classification problems. In this paper, we first reveal that the MU can even make the filter sizes halved in restoration problems thus leading to compaction of the network sizes. To show this, our SR network is designed without increasing the filter sizes with MU, which outperforms the state of the art SR methods with a smaller number of filter parameters. To the best of our knowledge, we are the first to incorporate MU into SR applications and show promising performance results. In MU, feature maps from a previous convolutional layer are divided into two parts along channels, which are then compared element-wise and only their max values are passed to a next layer. Along with some interesting properties of MU to be analyzed, we further investigate other variants of MU and their effects. In addition, while ReLU have a trouble for learning in networks with a very small number of convolutional filter parameters, MU do not. For SR applications, our MU-based network reconstructs high-resolution images with comparable quality compared to previous deep-learning-based SR methods, with lower filter parameters.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02321v2
PDF	http://arxiv.org/pdf/1711.02321v2.pdf
PWC	https://paperswithcode.com/paper/single-image-super-resolution-using
Repo
Framework

Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots


Title	Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots
Authors	Chen Zhou, Jiaolong Yang, Chunshui Zhao, Gang Hua
Abstract	Safety is paramount for mobile robotic platforms such as self-driving cars and unmanned aerial vehicles. This work is devoted to a task that is indispensable for safety yet was largely overlooked in the past – detecting obstacles that are of very thin structures, such as wires, cables and tree branches. This is a challenging problem, as thin objects can be problematic for active sensors such as lidar and sonar and even for stereo cameras. In this work, we propose to use video sequences for thin obstacle detection. We represent obstacles with edges in the video frames, and reconstruct them in 3D using efficient edge-based visual odometry techniques. We provide both a monocular camera solution and a stereo camera solution. The former incorporates Inertial Measurement Unit (IMU) data to solve scale ambiguity, while the latter enjoys a novel, purely vision-based solution. Experiments demonstrated that the proposed methods are fast and able to detect thin obstacles robustly and accurately under various conditions.
Tasks	Self-Driving Cars, Visual Odometry
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04006v1
PDF	http://arxiv.org/pdf/1708.04006v1.pdf
PWC	https://paperswithcode.com/paper/fast-accurate-thin-structure-obstacle
Repo
Framework