May 6, 2019

2854 words 14 mins read

Paper Group ANR 376

Neural Aggregation Network for Video Face Recognition. Deep Aesthetic Quality Assessment with Semantic Information. Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia. Multivariate Hawkes Processes for Large-scale Inference. You want to survive the data deluge: Be careful, Computational Intelligence will not ser …

Neural Aggregation Network for Video Face Recognition


Title	Neural Aggregation Network for Video Face Recognition
Authors	Jiaolong Yang, Peiran Ren, Dongqing Zhang, Dong Chen, Fang Wen, Hongdong Li, Gang Hua
Abstract	This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spanned by them. Due to the attention mechanism, the aggregation is invariant to the image order. Our NAN is trained with a standard classification or verification loss without any extra supervision signal, and we found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces. The experiments on IJB-A, YouTube Face, Celebrity-1000 video face recognition benchmarks show that it consistently outperforms naive aggregation methods and achieves the state-of-the-art accuracy.
Tasks	Face Recognition, Face Verification
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05474v4
PDF	http://arxiv.org/pdf/1603.05474v4.pdf
PWC	https://paperswithcode.com/paper/neural-aggregation-network-for-video-face
Repo
Framework

Deep Aesthetic Quality Assessment with Semantic Information


Title	Deep Aesthetic Quality Assessment with Semantic Information
Authors	Yueying Kao, Ran He, Kaiqi Huang
Abstract	Human beings often assess the aesthetic quality of an image coupled with the identification of the image’s semantic content. This paper addresses the correlation issue between automatic aesthetic quality assessment and semantic recognition. We cast the assessment problem as the main task among a multi-task deep model, and argue that semantic recognition task offers the key to address this problem. Based on convolutional neural networks, we employ a single and simple multi-task framework to efficiently utilize the supervision of aesthetic and semantic labels. A correlation item between these two tasks is further introduced to the framework by incorporating the inter-task relationship learning. This item not only provides some useful insight about the correlation but also improves assessment accuracy of the aesthetic task. Particularly, an effective strategy is developed to keep a balance between the two tasks, which facilitates to optimize the parameters of the framework. Extensive experiments on the challenging AVA dataset and Photo.net dataset validate the importance of semantic recognition in aesthetic quality assessment, and demonstrate that multi-task deep models can discover an effective aesthetic representation to achieve state-of-the-art results.
Tasks	Aesthetics Quality Assessment
Published	2016-04-18
URL	http://arxiv.org/abs/1604.04970v3
PDF	http://arxiv.org/pdf/1604.04970v3.pdf
PWC	https://paperswithcode.com/paper/deep-aesthetic-quality-assessment-with
Repo
Framework

Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia


Title	Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia
Authors	Evrim Acar, Yuri Levin-Schwartz, Vince D. Calhoun, Tülay Adalı
Abstract	Neuroimaging modalities such as functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) provide information about neurological functions in complementary spatiotemporal resolutions; therefore, fusion of these modalities is expected to provide better understanding of brain activity. In this paper, we jointly analyze fMRI and multi-channel EEG signals collected during an auditory oddball task with the goal of capturing brain activity patterns that differ between patients with schizophrenia and healthy controls. Rather than selecting a single electrode or matricizing the third-order tensor that can be naturally used to represent multi-channel EEG signals, we preserve the multi-way structure of EEG data and use a coupled matrix and tensor factorization (CMTF) model to jointly analyze fMRI and EEG signals. Our analysis reveals that (i) joint analysis of EEG and fMRI using a CMTF model can capture meaningful temporal and spatial signatures of patterns that behave differently in patients and controls, and (ii) these differences and the interpretability of the associated components increase by including multiple electrodes from frontal, motor and parietal areas, but not necessarily by including all electrodes in the analysis.
Tasks	EEG
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02189v1
PDF	http://arxiv.org/pdf/1612.02189v1.pdf
PWC	https://paperswithcode.com/paper/tensor-based-fusion-of-eeg-and-fmri-to
Repo
Framework

Multivariate Hawkes Processes for Large-scale Inference


Title	Multivariate Hawkes Processes for Large-scale Inference
Authors	Rémi Lemonnier, Kevin Scaman, Argyris Kalogeratos
Abstract	In this paper, we present a framework for fitting multivariate Hawkes processes for large-scale problems both in the number of events in the observed history $n$ and the number of event types $d$ (i.e. dimensions). The proposed Low-Rank Hawkes Process (LRHP) framework introduces a low-rank approximation of the kernel matrix that allows to perform the nonparametric learning of the $d^2$ triggering kernels using at most $O(ndr^2)$ operations, where $r$ is the rank of the approximation ($r \ll d,n$). This comes as a major improvement to the existing state-of-the-art inference algorithms that are in $O(nd^2)$. Furthermore, the low-rank approximation allows LRHP to learn representative patterns of interaction between event types, which may be valuable for the analysis of such complex processes in real world datasets. The efficiency and scalability of our approach is illustrated with numerical experiments on simulated as well as real datasets.
Tasks
Published	2016-02-26
URL	http://arxiv.org/abs/1602.08418v1
PDF	http://arxiv.org/pdf/1602.08418v1.pdf
PWC	https://paperswithcode.com/paper/multivariate-hawkes-processes-for-large-scale
Repo
Framework

You want to survive the data deluge: Be careful, Computational Intelligence will not serve you as a rescue boat


Title	You want to survive the data deluge: Be careful, Computational Intelligence will not serve you as a rescue boat
Authors	Emanuel Diamant
Abstract	We are at the dawn of a new era, where advances in computer power, broadband communication and digital sensor technologies have led to an unprecedented flood of data inundating our surrounding. It is generally believed that means such as Computational Intelligence will help to outlive these tough times. However, these hopes are improperly high. Computational Intelligence is a surprising composition of two mutually exclusive and contradicting constituents that could be coupled only if you disregard and neglect their controversies: “Computational” implies reliance on data processing and “Intelligence” implies reliance on information processing. Only those who are indifferent to data-information discrepancy can believe that such a combination can be viable. We do not believe in miracles, so we will try to share with you our reservations.
Tasks
Published	2016-07-20
URL	http://arxiv.org/abs/1607.05810v1
PDF	http://arxiv.org/pdf/1607.05810v1.pdf
PWC	https://paperswithcode.com/paper/you-want-to-survive-the-data-deluge-be
Repo
Framework

The Dichotomy for Conservative Constraint Satisfaction is Polynomially Decidable


Title	The Dichotomy for Conservative Constraint Satisfaction is Polynomially Decidable
Authors	Clément Carbonnel
Abstract	Given a fixed constraint language $\Gamma$, the conservative CSP over $\Gamma$ (denoted by c-CSP($\Gamma$)) is a variant of CSP($\Gamma$) where the domain of each variable can be restricted arbitrarily. A dichotomy is known for conservative CSP: for every fixed language $\Gamma$, c-CSP($\Gamma$) is either in P or NP-complete. However, the characterization of conservatively tractable languages is of algebraic nature and the naive recognition algorithm is super-exponential in the domain size. The main contribution of this paper is a polynomial-time algorithm that, given a constraint language $\Gamma$ as input, decides if c-CSP($\Gamma$) is tractable. In addition, if $\Gamma$ is proven tractable the algorithm also outputs its coloured graph, which contains valuable information on the structure of $\Gamma$.
Tasks
Published	2016-04-24
URL	http://arxiv.org/abs/1604.07063v2
PDF	http://arxiv.org/pdf/1604.07063v2.pdf
PWC	https://paperswithcode.com/paper/the-dichotomy-for-conservative-constraint
Repo
Framework

Learning Functions: When Is Deep Better Than Shallow


Title	Learning Functions: When Is Deep Better Than Shallow
Authors	Hrushikesh Mhaskar, Qianli Liao, Tomaso Poggio
Abstract	While the universal approximation property holds both for hierarchical and shallow networks, we prove that deep (hierarchical) networks can approximate the class of compositional functions with the same accuracy as shallow networks but with exponentially lower number of training parameters as well as VC-dimension. This theorem settles an old conjecture by Bengio on the role of depth in networks. We then define a general class of scalable, shift-invariant algorithms to show a simple and natural set of requirements that justify deep convolutional networks.
Tasks
Published	2016-03-03
URL	http://arxiv.org/abs/1603.00988v4
PDF	http://arxiv.org/pdf/1603.00988v4.pdf
PWC	https://paperswithcode.com/paper/learning-functions-when-is-deep-better-than
Repo
Framework

Neural Recovery Machine for Chinese Dropped Pronoun


Title	Neural Recovery Machine for Chinese Dropped Pronoun
Authors	Wei-Nan Zhang, Ting Liu, Qingyu Yin, Yu Zhang
Abstract	Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese, so that to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on both two heterogeneous datasets. Further experiment results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.
Tasks	Feature Engineering
Published	2016-05-07
URL	https://arxiv.org/abs/1605.02134v2
PDF	https://arxiv.org/pdf/1605.02134v2.pdf
PWC	https://paperswithcode.com/paper/neural-recovery-machine-for-chinese-dropped
Repo
Framework

Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization


Title	Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization
Authors	Alon Gonen, Shai Shalev-Shwartz
Abstract	We show that the average stability notion introduced by \cite{kearns1999algorithmic, bousquet2002stability} is invariant to data preconditioning, for a wide class of generalized linear models that includes most of the known exp-concave losses. In other words, when analyzing the stability rate of a given algorithm, we may assume the optimal preconditioning of the data. This implies that, at least from a statistical perspective, explicit regularization is not required in order to compensate for ill-conditioned data, which stands in contrast to a widely common approach that includes a regularization for analyzing the sample complexity of generalized linear models. Several important implications of our findings include: a) We demonstrate that the excess risk of empirical risk minimization (ERM) is controlled by the preconditioned stability rate. This immediately yields a relatively short and elegant proof for the fast rates attained by ERM in our context. b) We strengthen the recent bounds of \cite{hardt2015train} on the stability rate of the Stochastic Gradient Descent algorithm.
Tasks
Published	2016-01-15
URL	http://arxiv.org/abs/1601.04011v4
PDF	http://arxiv.org/pdf/1601.04011v4.pdf
PWC	https://paperswithcode.com/paper/average-stability-is-invariant-to-data
Repo
Framework

Multi-body Non-rigid Structure-from-Motion


Title	Multi-body Non-rigid Structure-from-Motion
Authors	Suryansh Kumar, Yuchao Dai, Hongdong Li
Abstract	Conventional structure-from-motion (SFM) research is primarily concerned with the 3D reconstruction of a single, rigidly moving object seen by a static camera, or a static and rigid scene observed by a moving camera –in both cases there are only one relative rigid motion involved. Recent progress have extended SFM to the areas of {multi-body SFM} (where there are {multiple rigid} relative motions in the scene), as well as {non-rigid SFM} (where there is a single non-rigid, deformable object or scene). Along this line of thinking, there is apparently a missing gap of “multi-body non-rigid SFM”, in which the task would be to jointly reconstruct and segment multiple 3D structures of the multiple, non-rigid objects or deformable scenes from images. Such a multi-body non-rigid scenario is common in reality (e.g. two persons shaking hands, multi-person social event), and how to solve it represents a natural {next-step} in SFM research. By leveraging recent results of subspace clustering, this paper proposes, for the first time, an effective framework for multi-body NRSFM, which simultaneously reconstructs and segments each 3D trajectory into their respective low-dimensional subspace. Under our formulation, 3D trajectories for each non-rigid structure can be well approximated with a sparse affine combination of other 3D trajectories from the same structure (self-expressiveness). We solve the resultant optimization with the alternating direction method of multipliers (ADMM). We demonstrate the efficacy of the proposed framework through extensive experiments on both synthetic and real data sequences. Our method clearly outperforms other alternative methods, such as first clustering the 2D feature tracks to groups and then doing non-rigid reconstruction in each group or first conducting 3D reconstruction by using single subspace assumption and then clustering the 3D trajectories into groups.
Tasks	3D Reconstruction
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04515v1
PDF	http://arxiv.org/pdf/1607.04515v1.pdf
PWC	https://paperswithcode.com/paper/multi-body-non-rigid-structure-from-motion
Repo
Framework

Recursive Partitioning for Personalization using Observational Data


Title	Recursive Partitioning for Personalization using Observational Data
Authors	Nathan Kallus
Abstract	We study the problem of learning to choose from m discrete treatment options (e.g., news item or medical drug) the one with best causal effect for a particular instance (e.g., user or patient) where the training data consists of passive observations of covariates, treatment, and the outcome of the treatment. The standard approach to this problem is regress and compare: split the training data by treatment, fit a regression model in each split, and, for a new instance, predict all m outcomes and pick the best. By reformulating the problem as a single learning task rather than m separate ones, we propose a new approach based on recursively partitioning the data into regimes where different treatments are optimal. We extend this approach to an optimal partitioning approach that finds a globally optimal partition, achieving a compact, interpretable, and impactful personalization model. We develop new tools for validating and evaluating personalization models on observational data and use these to demonstrate the power of our novel approaches in a personalized medicine and a job training application.
Tasks
Published	2016-08-31
URL	http://arxiv.org/abs/1608.08925v3
PDF	http://arxiv.org/pdf/1608.08925v3.pdf
PWC	https://paperswithcode.com/paper/recursive-partitioning-for-personalization
Repo
Framework

Automatic Detection of Small Groups of Persons, Influential Members, Relations and Hierarchy in Written Conversations Using Fuzzy Logic


Title	Automatic Detection of Small Groups of Persons, Influential Members, Relations and Hierarchy in Written Conversations Using Fuzzy Logic
Authors	French Pope III, Rouzbeh A. Shirvani, Mugizi Robert Rwebangira, Mohamed Chouikha, Ayo Taylor, Andres Alarcon Ramirez, Amirsina Torfi
Abstract	Nowadays a lot of data is collected in online forums. One of the key tasks is to determine the social structure of these online groups, for example the identification of subgroups within a larger group. We will approach the grouping of individual as a classification problem. The classifier will be based on fuzzy logic. The input to the classifier will be linguistic features and degree of relationships (among individuals). The output of the classifiers are the groupings of individuals. We also incorporate a method that ranks the members of the detected subgroup to identify the hierarchies in each subgroup. Data from the HBO television show The Wire is used to analyze the efficacy and usefulness of fuzzy logic based methods as alternative methods to classical statistical methods usually used for these problems. The proposed methodology could detect automatically the most influential members of each organization The Wire with 90% accuracy.
Tasks
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01720v1
PDF	http://arxiv.org/pdf/1610.01720v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-small-groups-of
Repo
Framework

Supervised Quantum Learning without Measurements


Title	Supervised Quantum Learning without Measurements
Authors	Unai Alvarez-Rodriguez, Lucas Lamata, Pablo Escandell-Montero, José D. Martín-Guerrero, Enrique Solano
Abstract	We propose a quantum machine learning algorithm for efficiently solving a class of problems encoded in quantum controlled unitary operations. The central physical mechanism of the protocol is the iteration of a quantum time-delayed equation that introduces feedback in the dynamics and eliminates the necessity of intermediate measurements. The performance of the quantum algorithm is analyzed by comparing the results obtained in numerical simulations with the outcome of classical machine learning methods for the same problem. The use of time-delayed equations enhances the toolbox of the field of quantum machine learning, which may enable unprecedented applications in quantum technologies.
Tasks	Quantum Machine Learning
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05535v2
PDF	http://arxiv.org/pdf/1612.05535v2.pdf
PWC	https://paperswithcode.com/paper/supervised-quantum-learning-without
Repo
Framework

Recursive Neural Language Architecture for Tag Prediction


Title	Recursive Neural Language Architecture for Tag Prediction
Authors	Saurabh Kataria
Abstract	We consider the problem of learning distributed representations for tags from their associated content for the task of tag recommendation. Considering tagging information is usually very sparse, effective learning from content and tag association is very crucial and challenging task. Recently, various neural representation learning models such as WSABIE and its variants show promising performance, mainly due to compact feature representations learned in a semantic space. However, their capacity is limited by a linear compositional approach for representing tags as sum of equal parts and hurt their performance. In this work, we propose a neural feedback relevance model for learning tag representations with weighted feature representations. Our experiments on two widely used datasets show significant improvement for quality of recommendations over various baselines.
Tasks	Representation Learning
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07646v1
PDF	http://arxiv.org/pdf/1603.07646v1.pdf
PWC	https://paperswithcode.com/paper/recursive-neural-language-architecture-for
Repo
Framework

Improving Power Generation Efficiency using Deep Neural Networks


Title	Improving Power Generation Efficiency using Deep Neural Networks
Authors	Stefan Hosein, Patrick Hosein
Abstract	Recently there has been significant research on power generation, distribution and transmission efficiency especially in the case of renewable resources. The main objective is reduction of energy losses and this requires improvements on data acquisition and analysis. In this paper we address these concerns by using consumers’ electrical smart meter readings to estimate network loading and this information can then be used for better capacity planning. We compare Deep Neural Network (DNN) methods with traditional methods for load forecasting. Our results indicate that DNN methods outperform most traditional methods. This comes at the cost of additional computational complexity but this can be addressed with the use of cloud resources. We also illustrate how these results can be used to better support dynamic pricing.
Tasks	Load Forecasting
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05018v1
PDF	http://arxiv.org/pdf/1606.05018v1.pdf
PWC	https://paperswithcode.com/paper/improving-power-generation-efficiency-using
Repo
Framework