July 28, 2019

2765 words 13 mins read

Paper Group ANR 189

Algorithms and Architecture for Real-time Recommendations at News UK. Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions. On the Performance of Forecasting Models in the Presence of Input Uncertainty. Feature Studies to Inform the Classification of Depressive Symptoms from Twitter Data for Population Health. Re …

Algorithms and Architecture for Real-time Recommendations at News UK


Title	Algorithms and Architecture for Real-time Recommendations at News UK
Authors	Dion Bailey, Tom Pajak, Daoud Clarke, Carlos Rodriguez
Abstract	Recommendation systems are recognised as being hugely important in industry, and the area is now well understood. At News UK, there is a requirement to be able to quickly generate recommendations for users on news items as they are published. However, little has been published about systems that can generate recommendations in response to changes in recommendable items and user behaviour in a very short space of time. In this paper we describe a new algorithm for updating collaborative filtering models incrementally, and demonstrate its effectiveness on clickstream data from The Times. We also describe the architecture that allows recommendations to be generated on the fly, and how we have made each component scalable. The system is currently being used in production at News UK.
Tasks	Recommendation Systems
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05278v1
PDF	http://arxiv.org/pdf/1709.05278v1.pdf
PWC	https://paperswithcode.com/paper/algorithms-and-architecture-for-real-time
Repo
Framework

Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions


Title	Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions
Authors	Pascal Mettes, Cees G. M. Snoek
Abstract	We aim for zero-shot localization and classification of human actions in video. Where traditional approaches rely on global attribute or object classification scores for their zero-shot knowledge transfer, our main contribution is a spatial-aware object embedding. To arrive at spatial awareness, we build our embedding on top of freely available actor and object detectors. Relevance of objects is determined in a word embedding space and further enforced with estimated spatial preferences. Besides local object awareness, we also embed global object awareness into our embedding to maximize actor and object interaction. Finally, we exploit the object positions and sizes in the spatial-aware embedding to demonstrate a new spatio-temporal action retrieval scenario with composite queries. Action localization and classification experiments on four contemporary action video datasets support our proposal. Apart from state-of-the-art results in the zero-shot localization and classification settings, our spatial-aware embedding is even competitive with recent supervised action localization alternatives.
Tasks	Action Localization, Object Classification, Transfer Learning
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09145v1
PDF	http://arxiv.org/pdf/1707.09145v1.pdf
PWC	https://paperswithcode.com/paper/spatial-aware-object-embeddings-for-zero-shot
Repo
Framework

On the Performance of Forecasting Models in the Presence of Input Uncertainty


Title	On the Performance of Forecasting Models in the Presence of Input Uncertainty
Authors	Hossein Sangrody, Morteza Sarailoo, Ning Zhou, Ahmad Shokrollahi, Elham Foruzan
Abstract	Nowadays, with the unprecedented penetration of renewable distributed energy resources (DERs), the necessity of an efficient energy forecasting model is more demanding than before. Generally, forecasting models are trained using observed weather data while the trained models are applied for energy forecasting using forecasted weather data. In this study, the performance of several commonly used forecasting methods in the presence of weather predictors with uncertainty is assessed and compared. Accordingly, both observed and forecasted weather data are collected, then the influential predictors for solar PV generation forecasting model are selected using several measures. Using observed and forecasted weather data, an analysis on the uncertainty of weather variables is represented by MAE and bootstrapping. The energy forecasting model is trained using observed weather data, and finally, the performance of several commonly used forecasting methods in solar energy forecasting is simulated and compared for a real case study.
Tasks
Published	2017-07-15
URL	http://arxiv.org/abs/1707.04692v1
PDF	http://arxiv.org/pdf/1707.04692v1.pdf
PWC	https://paperswithcode.com/paper/on-the-performance-of-forecasting-models-in
Repo
Framework

Feature Studies to Inform the Classification of Depressive Symptoms from Twitter Data for Population Health


Title	Feature Studies to Inform the Classification of Depressive Symptoms from Twitter Data for Population Health
Authors	Danielle Mowery, Craig Bryan, Mike Conway
Abstract	The utility of Twitter data as a medium to support population-level mental health monitoring is not well understood. In an effort to better understand the predictive power of supervised machine learning classifiers and the influence of feature sets for efficiently classifying depression-related tweets on a large-scale, we conducted two feature study experiments. In the first experiment, we assessed the contribution of feature groups such as lexical information (e.g., unigrams) and emotions (e.g., strongly negative) using a feature ablation study. In the second experiment, we determined the percentile of top ranked features that produced the optimal classification performance by applying a three-step feature elimination approach. In the first experiment, we observed that lexical features are critical for identifying depressive symptoms, specifically for depressed mood (-35 points) and for disturbed sleep (-43 points). In the second experiment, we observed that the optimal F1-score performance of top ranked features in percentiles variably ranged across classes e.g., fatigue or loss of energy (5th percentile, 288 features) to depressed mood (55th percentile, 3,168 features) suggesting there is no consistent count of features for predicting depressive-related tweets. We conclude that simple lexical features and reduced feature sets can produce comparable results to larger feature sets.
Tasks
Published	2017-01-28
URL	http://arxiv.org/abs/1701.08229v1
PDF	http://arxiv.org/pdf/1701.08229v1.pdf
PWC	https://paperswithcode.com/paper/feature-studies-to-inform-the-classification
Repo
Framework

Recency-weighted Markovian inference


Title	Recency-weighted Markovian inference
Authors	Kristjan Kalm
Abstract	We describe a Markov latent state space (MLSS) model, where the latent state distribution is a decaying mixture over multiple past states. We present a simple sampling algorithm that allows to approximate such high-order MLSS with fixed time and memory costs.
Tasks
Published	2017-11-08
URL	http://arxiv.org/abs/1711.03038v1
PDF	http://arxiv.org/pdf/1711.03038v1.pdf
PWC	https://paperswithcode.com/paper/recency-weighted-markovian-inference
Repo
Framework

Interactive Robot Learning of Gestures, Language and Affordances


Title	Interactive Robot Learning of Gestures, Language and Affordances
Authors	Giovanni Saponaro, Lorenzo Jamone, Alexandre Bernardino, Giampiero Salvi
Abstract	A growing field in robotics and Artificial Intelligence (AI) research is human-robot collaboration, whose target is to enable effective teamwork between humans and robots. However, in many situations human teams are still superior to human-robot teams, primarily because human teams can easily agree on a common goal with language, and the individual members observe each other effectively, leveraging their shared motor repertoire and sensorimotor resources. This paper shows that for cognitive robots it is possible, and indeed fruitful, to combine knowledge acquired from interacting with elements of the environment (affordance exploration) with the probabilistic observation of another agent’s actions. We propose a model that unites (i) learning robot affordances and word descriptions with (ii) statistical recognition of human gestures with vision sensors. We discuss theoretical motivations, possible implementations, and we show initial results which highlight that, after having acquired knowledge of its surrounding environment, a humanoid robot can generalize this knowledge to the case when it observes another agent (human partner) performing the same motor actions previously executed during training.
Tasks
Published	2017-11-24
URL	http://arxiv.org/abs/1711.09055v1
PDF	http://arxiv.org/pdf/1711.09055v1.pdf
PWC	https://paperswithcode.com/paper/interactive-robot-learning-of-gestures
Repo
Framework

DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images


Title	DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
Authors	Jameson Merkow, Robert Lufkin, Kim Nguyen, Stefano Soatto, Zhuowen Tu, Andrea Vedaldi
Abstract	We describe a system to automatically filter clinically significant findings from computerized tomography (CT) head scans, operating at performance levels exceeding that of practicing radiologists. Our system, named DeepRadiologyNet, builds on top of deep convolutional neural networks (CNNs) trained using approximately 3.5 million CT head images gathered from over 24,000 studies taken from January 1, 2015 to August 31, 2015 and January 1, 2016 to April 30 2016 in over 80 clinical sites. For our initial system, we identified 30 phenomenological traits to be recognized in the CT scans. To test the system, we designed a clinical trial using over 4.8 million CT head images (29,925 studies), completely disjoint from the training and validation set, interpreted by 35 US Board Certified radiologists with specialized CT head experience. We measured clinically significant error rates to ascertain whether the performance of DeepRadiologyNet was comparable to or better than that of US Board Certified radiologists. DeepRadiologyNet achieved a clinically significant miss rate of 0.0367% on automatically selected high-confidence studies. Thus, DeepRadiologyNet enables significant reduction in the workload of human radiologists by automatically filtering studies and reporting on the high-confidence ones at an operating point well below the literal error rate for US Board Certified radiologists, estimated at 0.82%.
Tasks
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09313v3
PDF	http://arxiv.org/pdf/1711.09313v3.pdf
PWC	https://paperswithcode.com/paper/deepradiologynet-radiologist-level-pathology
Repo
Framework

Spatial and Angular Resolution Enhancement of Light Fields Using Convolutional Neural Networks


Title	Spatial and Angular Resolution Enhancement of Light Fields Using Convolutional Neural Networks
Authors	M. Shahzeb Khan Gul, Bahadir K. Gunturk
Abstract	Light field imaging extends the traditional photography by capturing both spatial and angular distribution of light, which enables new capabilities, including post-capture refocusing, post-capture aperture control, and depth estimation from a single shot. Micro-lens array (MLA) based light field cameras offer a cost-effective approach to capture light field. A major drawback of MLA based light field cameras is low spatial resolution, which is due to the fact that a single image sensor is shared to capture both spatial and angular information. In this paper, we present a learning based light field enhancement approach. Both spatial and angular resolution of captured light field is enhanced using convolutional neural networks. The proposed method is tested with real light field data captured with a Lytro light field camera, clearly demonstrating spatial and angular resolution improvement.
Tasks	Depth Estimation
Published	2017-07-04
URL	http://arxiv.org/abs/1707.00815v2
PDF	http://arxiv.org/pdf/1707.00815v2.pdf
PWC	https://paperswithcode.com/paper/spatial-and-angular-resolution-enhancement-of
Repo
Framework

Unsupervised prototype learning in an associative-memory network


Title	Unsupervised prototype learning in an associative-memory network
Authors	Huiling Zhen, Shang-Nan Wang, Hai-Jun Zhou
Abstract	Unsupervised learning in a generalized Hopfield associative-memory network is investigated in this work. First, we prove that the (generalized) Hopfield model is equivalent to a semi-restricted Boltzmann machine with a layer of visible neurons and another layer of hidden binary neurons, so it could serve as the building block for a multilayered deep-learning system. We then demonstrate that the Hopfield network can learn to form a faithful internal representation of the observed samples, with the learned memory patterns being prototypes of the input data. Furthermore, we propose a spectral method to extract a small set of concepts (idealized prototypes) as the most concise summary or abstraction of the empirical data.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02848v2
PDF	http://arxiv.org/pdf/1704.02848v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-prototype-learning-in-an
Repo
Framework

Graph Convolutional Networks for Classification with a Structured Label Space


Title	Graph Convolutional Networks for Classification with a Structured Label Space
Authors	Meihao Chen, Zhuoru Lin, Kyunghyun Cho
Abstract	It is a usual practice to ignore any structural information underlying classes in multi-class classification. In this paper, we propose a graph convolutional network (GCN) augmented neural network classifier to exploit a known, underlying graph structure of labels. The proposed approach resembles an (approximate) inference procedure in, for instance, a conditional random field (CRF). We evaluate the proposed approach on document classification and object recognition and report both accuracies and graph-theoretic metrics that correspond to the consistency of the model’s prediction. The experiment results reveal that the proposed model outperforms a baseline method which ignores the graph structures of a label space in terms of graph-theoretic metrics.
Tasks	Document Classification, Object Recognition
Published	2017-10-12
URL	http://arxiv.org/abs/1710.04908v2
PDF	http://arxiv.org/pdf/1710.04908v2.pdf
PWC	https://paperswithcode.com/paper/graph-convolutional-networks-for
Repo
Framework

Improved Descriptors for Patch Matching and Reconstruction


Title	Improved Descriptors for Patch Matching and Reconstruction
Authors	Rahul Mitra, Jiakai Zhang, Sanath Narayan, Shuaib Ahmed, Sharat Chandran, Arjun Jain
Abstract	We propose a convolutional neural network (ConvNet) based approach for learning local image descriptors which can be used for significantly improved patch matching and 3D reconstructions. A multi-resolution ConvNet is used for learning keypoint descriptors. We also propose a new dataset consisting of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) [18] dataset. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. We evaluate our approach on publicly available datasets, such as Oxford Affine Covariant Regions Dataset (ACRD) [12], MVS [18], Synthetic [6] and Strecha [15] datasets to quantify the image descriptor performance. Scenes from the Oxford ACRD, MVS and Synthetic datasets are used for evaluating the patch matching performance of the learnt descriptors while the Strecha dataset is used to evaluate the 3D reconstruction task. Experiments show that the proposed descriptor outperforms the current state-of-the-art descriptors in both the evaluation tasks.
Tasks	3D Reconstruction
Published	2017-01-24
URL	http://arxiv.org/abs/1701.06854v4
PDF	http://arxiv.org/pdf/1701.06854v4.pdf
PWC	https://paperswithcode.com/paper/improved-descriptors-for-patch-matching-and
Repo
Framework

Shape Complementarity Analysis for Objects of Arbitrary Shape


Title	Shape Complementarity Analysis for Objects of Arbitrary Shape
Authors	Morad Behandish, Horea T. Ilies
Abstract	The basic problem of shape complementarity analysis appears fundamental to applications as diverse as mechanical design, assembly automation, robot motion planning, micro- and nano-fabrication, protein-ligand binding, and rational drug design. However, the current challenge lies in the lack of a general mathematical formulation that applies to objects of arbitrary shape. We propose that a measure of shape complementarity can be obtained from the extent of approximate overlap between shape skeletons. A space-continuous implicit generalization of the skeleton, called the skeletal density function (SDF) is defined over the Euclidean space that contains the individual assembly partners. The SDF shape descriptors capture the essential features that are relevant to proper contact alignment, and are considerably more robust than the conventional explicit skeletal representations. We express the shape complementarity score as a convolution of the individual SDFs. The problem then breaks down to a global optimization of the score over the configuration space of spatial relations, which can be efficiently implemented using fast Fourier transforms (FFTs) on nonequispaced samples. We demonstrate the effectiveness of the scoring approach for several examples from 2D peg-in-hole alignment to more complex 3D examples in mechanical assembly and protein docking. We show that the proposed method is reliable, inherently robust against small perturbations, and effective in steering gradient-based optimization.
Tasks	Motion Planning
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00238v1
PDF	http://arxiv.org/pdf/1712.00238v1.pdf
PWC	https://paperswithcode.com/paper/shape-complementarity-analysis-for-objects-of
Repo
Framework

Measuring Relations Between Concepts In Conceptual Spaces


Title	Measuring Relations Between Concepts In Conceptual Spaces
Authors	Lucas Bechberger, Kai-Uwe Kühnberger
Abstract	The highly influential framework of conceptual spaces provides a geometric way of representing knowledge. Instances are represented by points in a high-dimensional space and concepts are represented by regions in this space. Our recent mathematical formalization of this framework is capable of representing correlations between different domains in a geometric way. In this paper, we extend our formalization by providing quantitative mathematical definitions for the notions of concept size, subsethood, implication, similarity, and betweenness. This considerably increases the representational power of our formalization by introducing measurable ways of describing relations between concepts.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02292v2
PDF	http://arxiv.org/pdf/1707.02292v2.pdf
PWC	https://paperswithcode.com/paper/measuring-relations-between-concepts-in
Repo
Framework

Gradient Descent Can Take Exponential Time to Escape Saddle Points


Title	Gradient Descent Can Take Exponential Time to Escape Saddle Points
Authors	Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Barnabas Poczos, Aarti Singh
Abstract	Although gradient descent (GD) almost always escapes saddle points asymptotically [Lee et al., 2016], this paper shows that even with fairly natural random initialization schemes and non-pathological functions, GD can be significantly slowed down by saddle points, taking exponential time to escape. On the other hand, gradient descent with perturbations [Ge et al., 2015, Jin et al., 2017] is not slowed down by saddle points - it can find an approximate local minimizer in polynomial time. This result implies that GD is inherently slower than perturbed GD, and justifies the importance of adding perturbations for efficient non-convex optimization. While our focus is theoretical, we also present experiments that illustrate our theoretical findings.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10412v2
PDF	http://arxiv.org/pdf/1705.10412v2.pdf
PWC	https://paperswithcode.com/paper/gradient-descent-can-take-exponential-time-to
Repo
Framework

Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition


Title	Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
Authors	Naoya Takeishi, Yoshinobu Kawahara, Takehisa Yairi
Abstract	Spectral decomposition of the Koopman operator is attracting attention as a tool for the analysis of nonlinear dynamical systems. Dynamic mode decomposition is a popular numerical algorithm for Koopman spectral analysis; however, we often need to prepare nonlinear observables manually according to the underlying dynamics, which is not always possible since we may not have any a priori knowledge about them. In this paper, we propose a fully data-driven method for Koopman spectral analysis based on the principle of learning Koopman invariant subspaces from observed data. To this end, we propose minimization of the residual sum of squares of linear least-squares regression to estimate a set of functions that transforms data into a form in which the linear regression fits well. We introduce an implementation with neural networks and evaluate performance empirically using nonlinear dynamical systems and applications.
Tasks
Published	2017-10-12
URL	http://arxiv.org/abs/1710.04340v2
PDF	http://arxiv.org/pdf/1710.04340v2.pdf
PWC	https://paperswithcode.com/paper/learning-koopman-invariant-subspaces-for
Repo
Framework