Paper Group ANR 494
![Paper Group ANR 494](/2018/images/pwc/paper-arxiv_hu144ec288a26b3e360d673e256787de3e_28623_900x500_fit_q75_box.jpg)
Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner. Semantic WordRank: Generating Finer Single-Document Summarizations. Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network. Designing Optimal Binary Rating Systems. Thermodynamics and Feature Extraction …
Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner
Title | Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner |
Authors | Nicolas Duminy, Sao Mai Nguyen, Dominique Duhaut |
Abstract | We propose an active learning architecture for robots, capable of organizing its learning process to achieve a field of complex tasks by learning sequences of motor policies, called Intrinsically Motivated Procedure Babbling (IM-PB). The learner can generalize over its experience to continuously learn new tasks. It chooses actively what and how to learn based by empirical measures of its own progress. In this paper, we are considering the learning of a set of interrelated tasks outcomes hierarchically organized. We introduce a framework called ‘procedures’, which are sequences of policies defined by the combination of previously learned skills. Our algorithmic architecture uses the procedures to autonomously discover how to combine simple skills to achieve complex goals. It actively chooses between 2 strategies of goal-directed exploration : exploration of the policy space or the procedural space. We show on a simulated environment that our new architecture is capable of tackling the learning of complex motor policies, to adapt the complexity of its policies to the task at hand. We also show that our ‘procedures’ framework helps the learner to tackle difficult hierarchical tasks. |
Tasks | Active Learning |
Published | 2018-10-11 |
URL | http://arxiv.org/abs/1810.04877v2 |
http://arxiv.org/pdf/1810.04877v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-a-set-of-interrelated-tasks-by-using |
Repo | |
Framework | |
Semantic WordRank: Generating Finer Single-Document Summarizations
Title | Semantic WordRank: Generating Finer Single-Document Summarizations |
Authors | Hao Zhang, Jie Wang |
Abstract | We present Semantic WordRank (SWR), an unsupervised method for generating an extractive summary of a single document. Built on a weighted word graph with semantic and co-occurrence edges, SWR scores sentences using an article-structure-biased PageRank algorithm with a Softplus function adjustment, and promotes topic diversity using spectral subtopic clustering under the Word-Movers-Distance metric. We evaluate SWR on the DUC-02 and SummBank datasets and show that SWR produces better summaries than the state-of-the-art algorithms over DUC-02 under common ROUGE measures. We then show that, under the same measures over SummBank, SWR outperforms each of the three human annotators (aka. judges) and compares favorably with the combined performance of all judges. |
Tasks | |
Published | 2018-09-12 |
URL | http://arxiv.org/abs/1809.04649v1 |
http://arxiv.org/pdf/1809.04649v1.pdf | |
PWC | https://paperswithcode.com/paper/semantic-wordrank-generating-finer-single |
Repo | |
Framework | |
Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network
Title | Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network |
Authors | Chenying Wang, Li Yu, Shengwei Wang |
Abstract | High efficiency video coding (HEVC) suffers high encoding computational complexity, partly attributed to the rate-distortion optimization quad-tree search in CU partition decision. Therefore, we propose a novel two-stage CU partition decision approach in HEVC intra-mode. In the proposed approach, CNN-based algorithm is designed to decide CU partition mode precisely in three depths. In order to alleviate computational complexity further, an auxiliary earl-termination mechanism is also proposed to filter obvious homogeneous CUs out of the subsequent CNN-based algorithm. Experimental results show that the proposed approach achieves about 37% encoding time saving on average and insignificant BD-Bitrate rise compared with the original HEVC encoder. |
Tasks | |
Published | 2018-09-23 |
URL | http://arxiv.org/abs/1809.08617v1 |
http://arxiv.org/pdf/1809.08617v1.pdf | |
PWC | https://paperswithcode.com/paper/accelerate-cu-partition-in-hevc-using-large |
Repo | |
Framework | |
Designing Optimal Binary Rating Systems
Title | Designing Optimal Binary Rating Systems |
Authors | Nikhil Garg, Ramesh Johari |
Abstract | Modern online platforms rely on effective rating systems to learn about items. We consider the optimal design of rating systems that collect binary feedback after transactions. We make three contributions. First, we formalize the performance of a rating system as the speed with which it recovers the true underlying ranking on items (in a large deviations sense), accounting for both items’ underlying match rates and the platform’s preferences. Second, we provide an efficient algorithm to compute the binary feedback system that yields the highest such performance. Finally, we show how this theoretical perspective can be used to empirically design an implementable, approximately optimal rating system, and validate our approach using real-world experimental data collected on Amazon Mechanical Turk. |
Tasks | |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06908v3 |
http://arxiv.org/pdf/1806.06908v3.pdf | |
PWC | https://paperswithcode.com/paper/designing-optimal-binary-rating-systems |
Repo | |
Framework | |
Thermodynamics and Feature Extraction by Machine Learning
Title | Thermodynamics and Feature Extraction by Machine Learning |
Authors | Shotaro Shiba Funai, Dimitrios Giataganas |
Abstract | Machine learning methods are powerful in distinguishing different phases of matter in an automated way and provide a new perspective on the study of physical phenomena. We train a Restricted Boltzmann Machine (RBM) on data constructed with spin configurations sampled from the Ising Hamiltonian at different values of temperature and external magnetic field using Monte Carlo methods. From the trained machine we obtain the flow of iterative reconstruction of spin state configurations to faithfully reproduce the observables of the physical system. We find that the flow of the trained RBM approaches the spin configurations of the maximal possible specific heat which resemble the near criticality region of the Ising model. In the special case of the vanishing magnetic field the trained RBM converges to the critical point of the Renormalization Group (RG) flow of the lattice model. Our results suggest an alternative explanation of how the machine identifies the physical phase transitions, by recognizing certain properties of the configuration like the maximization of the specific heat, instead of associating directly the recognition procedure with the RG flow and its fixed points. Then from the reconstructed data we deduce the critical exponent associated to the magnetization to find satisfactory agreement with the actual physical value. We assume no prior knowledge about the criticality of the system and its Hamiltonian. |
Tasks | |
Published | 2018-10-18 |
URL | http://arxiv.org/abs/1810.08179v1 |
http://arxiv.org/pdf/1810.08179v1.pdf | |
PWC | https://paperswithcode.com/paper/thermodynamics-and-feature-extraction-by |
Repo | |
Framework | |
Topology Estimation using Graphical Models in Multi-Phase Power Distribution Grids
Title | Topology Estimation using Graphical Models in Multi-Phase Power Distribution Grids |
Authors | Deepjyoti Deka, Michael Chertkov, Scott Backhaus |
Abstract | Distribution grid is the medium and low voltage part of a large power system. Structurally, the majority of distribution networks operate radially, such that energized lines form a collection of trees, i.e. forest, with a substation being at the root of any tree. The operational topology/forest may change from time to time, however tracking these changes, even though important for the distribution grid operation and control, is hindered by limited real-time monitoring. This paper develops a learning framework to reconstruct radial operational structure of the distribution grid from synchronized voltage measurements in the grid subject to the exogenous fluctuations in nodal power consumption. To detect operational lines our learning algorithm uses conditional independence tests for continuous random variables that is applicable to a wide class of probability distributions of the nodal consumption and Gaussian injections in particular. Moreover, our algorithm applies to the practical case of unbalanced three-phase power flow. Algorithm performance is validated on AC power flow simulations over IEEE distribution grid test cases. |
Tasks | |
Published | 2018-03-17 |
URL | http://arxiv.org/abs/1803.06531v2 |
http://arxiv.org/pdf/1803.06531v2.pdf | |
PWC | https://paperswithcode.com/paper/topology-estimation-using-graphical-models-in |
Repo | |
Framework | |
DLL: A Blazing Fast Deep Neural Network Library
Title | DLL: A Blazing Fast Deep Neural Network Library |
Authors | Baptiste Wicht, Jean Hennebert, Andreas Fischer |
Abstract | Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann Machines (RBMs) and Convolutional RBMs. Our main motivation for this work was to propose and evaluate novel software engineering strategies with potential to accelerate runtime for training and inference. Such strategies are mostly independent of the underlying deep learning algorithms. On three different datasets and for four different neural network models, we compared DLL to five popular deep learning frameworks. Experimentally, it is shown that the proposed framework is systematically and significantly faster on CPU and GPU. In terms of classification performance, similar accuracies as the other frameworks are reported. |
Tasks | |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.04512v1 |
http://arxiv.org/pdf/1804.04512v1.pdf | |
PWC | https://paperswithcode.com/paper/dll-a-blazing-fast-deep-neural-network |
Repo | |
Framework | |
Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence
Title | Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence |
Authors | Maryam Aziz, Jesse Anderton, Emilie Kaufmann, Javed Aslam |
Abstract | We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir distribution. We (1) introduce a PAC-like framework within which to derive and cast results; (2) derive a sample complexity lower bound for near-optimal arm identification; (3) propose an algorithm that identifies a nearly-optimal arm with high probability and derive an upper bound on its sample complexity which is within a log factor of our lower bound; and (4) discuss whether our log^2(1/delta) dependence is inescapable for “two-phase” (select arms first, identify the best later) algorithms in the infinite setting. This work permits the application of bandit models to a broader class of problems where fewer assumptions hold. |
Tasks | |
Published | 2018-03-13 |
URL | http://arxiv.org/abs/1803.04665v1 |
http://arxiv.org/pdf/1803.04665v1.pdf | |
PWC | https://paperswithcode.com/paper/pure-exploration-in-infinitely-armed-bandit |
Repo | |
Framework | |
Driving Experience Transfer Method for End-to-End Control of Self-Driving Cars
Title | Driving Experience Transfer Method for End-to-End Control of Self-Driving Cars |
Authors | Dooseop Choi, Taeg-Hyun An, Kyounghwan Ahn, Jeongdan Choi |
Abstract | In this paper, we present a transfer learning method for the end-to-end control of self-driving cars, which enables a convolutional neural network (CNN) trained on a source domain to be utilized for the same task in a different target domain. A conventional CNN for the end-to-end control is designed to map a single front-facing camera image to a steering command. To enable the transfer learning, we let the CNN produce not only a steering command but also a lane departure level (LDL) by adding a new task module, which takes the output of the last convolutional layer as input. The CNN trained on the source domain, called source network, is then utilized to train another task module called target network, which also takes the output of the last convolutional layer of the source network and is trained to produce a steering command for the target domain. The steering commands from the source and target network are finally merged according to the LDL and the merged command is utilized for controlling a car in the target domain. To demonstrate the effectiveness of the proposed method, we utilized two simulators, TORCS and GTAV, for the source and the target domains, respectively. Experimental results show that the proposed method outperforms other baseline methods in terms of stable and safe control of cars. |
Tasks | Self-Driving Cars, Transfer Learning |
Published | 2018-09-06 |
URL | http://arxiv.org/abs/1809.01822v2 |
http://arxiv.org/pdf/1809.01822v2.pdf | |
PWC | https://paperswithcode.com/paper/driving-experience-transfer-method-for-end-to |
Repo | |
Framework | |
Using semantic clustering to support situation awareness on Twitter: The case of World Views
Title | Using semantic clustering to support situation awareness on Twitter: The case of World Views |
Authors | Charlie Kingston, Jason R. C. Nurse, Ioannis Agrafiotis, Andrew Milich |
Abstract | In recent years, situation awareness has been recognised as a critical part of effective decision making, in particular for crisis management. One way to extract value and allow for better situation awareness is to develop a system capable of analysing a dataset of multiple posts, and clustering consistent posts into different views or stories (or, world views). However, this can be challenging as it requires an understanding of the data, including determining what is consistent data, and what data corroborates other data. Attempting to address these problems, this article proposes Subject-Verb-Object Semantic Suffix Tree Clustering (SVOSSTC) and a system to support it, with a special focus on Twitter content. The novelty and value of SVOSSTC is its emphasis on utilising the Subject-Verb-Object (SVO) typology in order to construct semantically consistent world views, in which individuals—particularly those involved in crisis response—might achieve an enhanced picture of a situation from social media data. To evaluate our system and its ability to provide enhanced situation awareness, we tested it against existing approaches, including human data analysis, using a variety of real-world scenarios. The results indicated a noteworthy degree of evidence (e.g., in cluster granularity and meaningfulness) to affirm the suitability and rigour of our approach. Moreover, these results highlight this article’s proposals as innovative and practical system contributions to the research field. |
Tasks | Decision Making |
Published | 2018-07-17 |
URL | http://arxiv.org/abs/1807.06588v1 |
http://arxiv.org/pdf/1807.06588v1.pdf | |
PWC | https://paperswithcode.com/paper/using-semantic-clustering-to-support |
Repo | |
Framework | |
Topology guaranteed segmentation of the human retina from OCT using convolutional neural networks
Title | Topology guaranteed segmentation of the human retina from OCT using convolutional neural networks |
Authors | Yufan He, Aaron Carass, Bruno M. Jedynak, Sharon D. Solomon, Shiv Saidha, Peter A. Calabresi, Jerry L. Prince |
Abstract | Optical coherence tomography (OCT) is a noninvasive imaging modality which can be used to obtain depth images of the retina. The changing layer thicknesses can thus be quantified by analyzing these OCT images, moreover these changes have been shown to correlate with disease progression in multiple sclerosis. Recent automated retinal layer segmentation tools use machine learning methods to perform pixel-wise labeling and graph methods to guarantee the layer hierarchy or topology. However, graph parameters like distance and smoothness constraints must be experimentally assigned by retinal region and pathology, thus degrading the flexibility and time efficiency of the whole framework. In this paper, we develop cascaded deep networks to provide a topologically correct segmentation of the retinal layers in a single feed forward propagation. The first network (S-Net) performs pixel-wise labeling and the second regression network (R-Net) takes the topologically unconstrained S-Net results and outputs layer thicknesses for each layer and each position. Relu activation is used as the final operation of the R-Net which guarantees non-negativity of the output layer thickness. Since the segmentation boundary position is acquired by summing up the corresponding non-negative layer thicknesses, the layer ordering (i.e., topology) of the reconstructed boundaries is guaranteed even at the fovea where the distances between boundaries can be zero. The R-Net is trained using simulated masks and thus can be generalized to provide topology guaranteed segmentation for other layered structures. This deep network has achieved comparable mean absolute boundary error (2.82 {\mu}m) to state-of-the-art graph methods (2.83 {\mu}m). |
Tasks | |
Published | 2018-03-14 |
URL | http://arxiv.org/abs/1803.05120v1 |
http://arxiv.org/pdf/1803.05120v1.pdf | |
PWC | https://paperswithcode.com/paper/topology-guaranteed-segmentation-of-the-human |
Repo | |
Framework | |
Higher-order Network for Action Recognition
Title | Higher-order Network for Action Recognition |
Authors | Kai Hu, Bhiksha Raj |
Abstract | Capturing spatiotemporal dynamics is an essential topic in video recognition. In this paper, we present learnable higher-order operations as a generic family of building blocks for capturing spatiotemporal dynamics from RGB input video space. Similar to higher-order functions, the weights of higher-order operations are themselves derived from the data with learnable parameters. Classical architectures such as residual learning and network-in-network are first-order operations where weights are directly learned from the data. Higher-order operations make it easier to capture context-sensitive patterns, such as motion. Self-attention models are also higher-order operations, but the attention weights are mostly computed from an affine operation or dot product. Learnable higher-order operations can be more generic and flexible. Experimentally, we show that on the task of video recognition, our higher-order models can achieve results on par with or better than the existing state-of-the-art methods on Something-Something (V1 and V2), Kinetics and Charades datasets. |
Tasks | Video Classification, Video Recognition |
Published | 2018-11-19 |
URL | https://arxiv.org/abs/1811.07519v4 |
https://arxiv.org/pdf/1811.07519v4.pdf | |
PWC | https://paperswithcode.com/paper/high-order-neural-networks-for-video |
Repo | |
Framework | |
Morph: Flexible Acceleration for 3D CNN-based Video Understanding
Title | Morph: Flexible Acceleration for 3D CNN-based Video Understanding |
Authors | Kartik Hegde, Rohit Agrawal, Yulun Yao, Christopher W. Fletcher |
Abstract | The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition has received far less attention as an accelerator target. This is surprising, as video recognition is more computationally intensive than image recognition, and video traffic is predicted to be the majority of internet traffic in the coming years. This paper fills the gap between algorithmic and hardware advances for video recognition by providing a design space exploration and flexible architecture for accelerating 3D Convolutional Neural Networks (3D CNNs) - the core kernel in modern video understanding. When compared to (2D) CNNs used for image recognition, efficiently accelerating 3D CNNs poses a significant engineering challenge due to their large (and variable over time) memory footprint and higher dimensionality. To address these challenges, we design a novel accelerator, called Morph, that can adaptively support different spatial and temporal tiling strategies depending on the needs of each layer of each target 3D CNN. We codesign a software infrastructure alongside the Morph hardware to find good-fit parameters to control the hardware. Evaluated on state-of-the-art 3D CNNs, Morph achieves up to 3.4x (2.5x average) reduction in energy consumption and improves performance/watt by up to 5.1x (4x average) compared to a baseline 3D CNN accelerator, with an area overhead of 5%. Morph further achieves a 15.9x average energy reduction on 3D CNNs when compared to Eyeriss. |
Tasks | Video Recognition, Video Understanding |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.06807v1 |
http://arxiv.org/pdf/1810.06807v1.pdf | |
PWC | https://paperswithcode.com/paper/morph-flexible-acceleration-for-3d-cnn-based |
Repo | |
Framework | |
Stochastic Constraint Optimization using Propagation on Ordered Binary Decision Diagrams
Title | Stochastic Constraint Optimization using Propagation on Ordered Binary Decision Diagrams |
Authors | Anna L. D. Latour, Behrouz Babaki, Siegfried Nijssen |
Abstract | A number of problems in relational Artificial Intelligence can be viewed as Stochastic Constraint Optimization Problems (SCOPs). These are constraint optimization problems that involve objectives or constraints with a stochastic component. Building on the recently proposed language SC-ProbLog for modeling SCOPs, we propose a new method for solving these problems. Earlier methods used Probabilistic Logic Programming (PLP) techniques to create Ordered Binary Decision Diagrams (OBDDs), which were decomposed into smaller constraints in order to exploit existing constraint programming (CP) solvers. We argue that this approach has as drawback that a decomposed representation of an OBDD does not guarantee domain consistency during search, and hence limits the efficiency of the solver. For the specific case of monotonic distributions, we suggest an alternative method for using CP in SCOP, based on the development of a new propagator; we show that this propagator is linear in the size of the OBDD, and has the potential to be more efficient than the decomposition method, as it maintains domain consistency. |
Tasks | |
Published | 2018-07-03 |
URL | http://arxiv.org/abs/1807.01079v1 |
http://arxiv.org/pdf/1807.01079v1.pdf | |
PWC | https://paperswithcode.com/paper/stochastic-constraint-optimization-using |
Repo | |
Framework | |
Can Deep Learning Predict Risky Retail Investors? A Case Study in Financial Risk Behavior Forecasting
Title | Can Deep Learning Predict Risky Retail Investors? A Case Study in Financial Risk Behavior Forecasting |
Authors | Yaodong Yang, Alisa Kolesnikova, Stefan Lessmann, Tiejun Ma, Ming-Chien Sung, Johnnie E. V. Johnson |
Abstract | The paper examines the potential of deep learning to support decisions in financial risk management. We develop a deep learning model for predicting whether individual spread traders secure profits from future trades. This task embodies typical modeling challenges faced in risk and behavior forecasting. Conventional machine learning requires data that is representative of the feature-target relationship and relies on the often costly development, maintenance, and revision of handcrafted features. Consequently, modeling highly variable, heterogeneous patterns such as trader behavior is challenging. Deep learning promises a remedy. Learning hierarchical distributed representations of the data in an automatic manner (e.g. risk taking behavior), it uncovers generative features that determine the target (e.g., trader’s profitability), avoids manual feature engineering, and is more robust toward change (e.g. dynamic market conditions). The results of employing a deep network for operational risk forecasting confirm the feature learning capability of deep learning, provide guidance on designing a suitable network architecture and demonstrate the superiority of deep learning over machine learning and rule-based benchmarks. |
Tasks | Feature Engineering |
Published | 2018-12-14 |
URL | https://arxiv.org/abs/1812.06175v3 |
https://arxiv.org/pdf/1812.06175v3.pdf | |
PWC | https://paperswithcode.com/paper/can-deep-learning-predict-risky-retail |
Repo | |
Framework | |