Knowledge Consensus in complex networks: the role of learning
To reach consensus among interacting agents is a problem of interest for social, economical, and political systems. A computational and mathematical framework to investigate consensus dynamics on complex networks is naming games. In general, naming is not an independent process but relies on perception and categorization. Existing works focus on consensus process of vocabulary evolution in a population of agents. However, in order to name an object, agents must first be able to distinguish objects according to their features. We articulate a likelihood category game model (LCGM) to integrate feature learning and the naming process. In the LCGM, self-organized agents can define category based on acquired knowledge through learning and use likelihood estimation to distinguish objects. The information communicated among the agents is no longer simply in some form of absolute answer, but involves one’s perception. Extensive simulations with LCGM reveal that a more complex knowledge makes it harder to reach consensus. We also find that agents with larger degree contribute more to the knowledge formation and are more likely to be intelligent. The proposed LCGM and the findings provide new insights into the emergence and evolution of consensus in complex systems in general.
Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA
FPGA becomes a popular technology for implementing Convolutional Neural Network (CNN) in recent years. Most CNN applications on FPGA are domain-specific, e.g., detecting objects from specific categories, in which commonly-used CNN models pre-trained on general datasets may not be efficient enough. This paper presents TuRF, an end-to-end CNN acceleration framework to efficiently deploy domain-specific applications on FPGA by transfer learning that adapts pre-trained models to specific domains, replacing standard convolution layers with efficient convolution blocks, and applying layer fusion to enhance hardware design performance. We evaluate TuRF by deploying a pre-trained VGG-16 model for a domain-specific image recognition task onto a Stratix V FPGA. Results show that designs generated by TuRF achieve better performance than prior methods for the original VGG-16 and ResNet-50 models, while for the optimised VGG-16 model TuRF designs are more accurate and easier to process.
Feature Learning for Meta-Paths in Knowledge Graphs
In this thesis, we study the problem of feature learning on heterogeneous knowledge graphs. These features can be used to perform tasks such as link prediction, classification and clustering on graphs. Knowledge graphs provide rich semantics encoded in the edge and node types. Meta-paths consist of these types and abstract paths in the graph. Until now, meta-paths can only be used as categorical features with high redundancy and are therefore unsuitable for machine learning models. We propose meta-path embeddings to solve this problem by learning semantical and compact vector representations of them. Current graph embedding methods only embed nodes and edge types and therefore miss semantics encoded in the combination of them. Our method embeds meta-paths using the skipgram model with an extension to deal with the redundancy and high amount of meta-paths in big knowledge graphs. We critically evaluate our embedding approach by predicting links on Wikidata. The experiments indicate that we learn a sensible embedding of the meta-paths but can improve it further.
Action-conditional Sequence Modeling for Recommendation
In many online applications interactions between a user and a web-service are organized in a sequential way, e.g., user browsing an e-commerce website. In this setting, recommendation system acts throughout user navigation by showing items. Previous works have addressed this recommendation setup through the task of predicting the next item user will interact with. In particular, Recurrent Neural Networks (RNNs) has been shown to achieve substantial improvements over collaborative filtering baselines. In this paper, we consider interactions triggered by the recommendations of deployed recommender system in addition to browsing behavior. Indeed, it is reported that in online services interactions with recommendations represent up to 30\% of total interactions. Moreover, in practice, recommender system can greatly influence user behavior by promoting specific items. In this paper, we extend the RNN modeling framework by taking into account user interaction with recommended items. We propose and evaluate RNN architectures that consist of the recommendation action module and the state-action fusion module. Using real-world large-scale datasets we demonstrate improved performance on the next item prediction task compared to the baselines.
Unity: A General Platform for Intelligent Agents
Recent advances in Deep Reinforcement Learning and Robotics have been driven by the presence of increasingly realistic and complex simulation environments. Many of the existing platforms, however, provide either unrealistic visuals, inaccurate physics, low task complexity, or a limited capacity for interaction among artificial agents. Furthermore, many platforms lack the ability to flexibly configure the simulation, hence turning the simulation environment into a black-box from the perspective of the learning system. Here we describe a new open source toolkit for creating and interacting with simulation environments using the Unity platform: Unity ML-Agents Toolkit. By taking advantage of Unity as a simulation platform, the toolkit enables the development of learning environments which are rich in sensory and physical complexity, provide compelling cognitive challenges, and support dynamic multi-agent interaction. We detail the platform design, communication protocol, set of example environments, and variety of training scenarios made possible via the toolkit.
A Transfer-Learnable Natural Language Interface for Databases
Relational database management systems (RDBMSs) are powerful because they are able to optimize and answer queries against any relational database. A natural language interface (NLI) for a database, on the other hand, is tailored to support that specific database. In this work, we introduce a general purpose transfer-learnable NLI with the goal of learning one model that can be used as NLI for any relational database. We adopt the data management principle of separating data and its schema, but with the additional support for the idiosyncrasy and complexity of natural languages. Specifically, we introduce an automatic annotation mechanism that separates the schema and the data, where the schema also covers knowledge about natural language. Furthermore, we propose a customized sequence model that translates annotated natural language queries to SQL statements. We show in experiments that our approach outperforms previous NLI methods on the WikiSQL dataset and the model we learned can be applied to another benchmark dataset OVERNIGHT without retraining.
Are You Sure YouWant To Do That? Classification with Verification
Classification systems typically act in isolation, meaning they are required to implicitly memorize the characteristics of all candidate classes in order to classify. The cost of this is increased memory usage and poor sample efficiency. We propose a model which instead verifies using reference images during the classification process, reducing the burden of memorization. The model uses iterative nondifferentiable queries in order to classify an image. We demonstrate that such a model is feasible to train and can match baseline accuracy while being more parameter efficient. However, we show that finding the correct balance between image recognition and verification is essential to pushing the model towards desired behavior, suggesting that a pipeline of recognition followed by verification is a more promising approach.
dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need of capturing dynamics for prediction on a toy data set created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real world data sets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction.
Open Set Adversarial Examples
Adversarial examples in recent works target at closed set recognition systems, in which the training and testing classes are identical. In real-world scenarios, however, the testing classes may have limited, if any, overlap with the training classes, a problem named open set recognition. To our knowledge, the community does not have a specific design of adversarial examples targeting at this practical setting. Arguably, the new setting compromises traditional closed set attack methods in two aspects. First, closed set attack methods are based on classification and target at classification as well, but the open set problem suggests a different task, \emph{i.e.,} retrieval. It is undesirable that the generation mechanism of closed set recognition is different from the aim of open set recognition. Second, given that the query image is usually of an unseen class, predicting its category from the training classes is not reasonable, which leads to an inferior adversarial gradient. In this work, we view open set recognition as a retrieval task and propose a new approach, Opposite-Direction Feature Attack (ODFA), to generate adversarial examples / queries. When using an attacked example as query, we aim that the true matches be ranked as low as possible. In addressing the two limitations of closed set attack methods, ODFA directly works on the features for retrieval. The idea is to push away the feature of the adversarial query in the opposite direction of the original feature. Albeit simple, ODFA leads to a larger drop in Recall@K and mAP than the close-set attack methods on two open set recognition datasets, \emph{i.e.,} Market-1501 and CUB-200-2011. We also demonstrate that the attack performance of ODFA is not evidently superior to the state-of-the-art methods under closed set recognition (Cifar-10), suggesting its specificity for open set problems.
Coherence-Aware Neural Topic Modeling
Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However, topic coherence, owing to its challenging computation, is not optimized for and is only evaluated after training. In this work, under a neural variational inference framework, we propose methods to incorporate a topic coherence objective into the training process. We demonstrate that such a coherence-aware topic model exhibits a similar level of perplexity as baseline models but achieves substantially higher topic coherence.
The smoothness test for a density function
Optimizing CNN Model Inference on CPUs
The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs imply that better performance of CNN model inference on CPUs can deliver significant gain to a large number of users. The current approach to improving the performance of CNN model inference on CPUs relies on the use of a hardware-specific library of low-level operations such as Intel MKL-DNN and some basic model-level optimizations, which is restrictive and misses the opportunity to optimize the end-to-end inference pipeline as a whole. This paper proposes a more comprehensive approach of CNN model inference on CPUs that employs a full-stack and systematic scheme of operation-level and model-level optimizations coupled with efficient data layout transformations. Experiments show that our solution achieves up to 2.81x better latency for CNN model inference on a 18-core Intel Platinum 8000-series CPU compared to the state-of-the-art implementations using Intel MKL-DNN.
Textual Analogy Parsing: What’s Shared and What’s Compared among Analogous Facts
To understand a sentence like ‘whereas only 10% of White Americans live at or below the poverty line, 28% of African Americans do’ it is important not only to identify individual facts, e.g., poverty rates of distinct demographic groups, but also the higher-order relations between them, e.g., the disparity between them. In this paper, we propose the task of Textual Analogy Parsing (TAP) to model this higher-order meaning. The output of TAP is a frame-style meaning representation which explicitly specifies what is shared (e.g., poverty rates) and what is compared (e.g., White Americans vs. African Americans, 10% vs. 28%) between its component facts. Such a meaning representation can enable new applications that rely on discourse understanding such as automated chart generation from quantitative text. We present a new dataset for TAP, baselines, and a model that successfully uses an ILP to enforce the structural constraints of the problem.
What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
Nature language inference (NLI) task is a predictive task of determining the inference relationship of a pair of natural language sentences. With the increasing popularity of NLI, many state-of-the-art predictive models have been proposed with impressive performances. However, several works have noticed the statistical irregularities in the collected NLI data set that may result in an over-estimated performance of these models and proposed remedies. In this paper, we further investigate the statistical irregularities, what we refer as confounding factors, of the NLI data sets. With the belief that some NLI labels should preserve under swapping operations, we propose a simple yet effective way (swapping the two text fragments) of evaluating the NLI predictive models that naturally mitigate the observed problems. Further, we continue to train the predictive models with our swapping manner and propose to use the deviation of the model’s evaluation performances under different percentages of training text fragments to be swapped to describe the robustness of a predictive model. Our evaluation metrics leads to some interesting understandings of recent published NLI methods. Finally, we also apply the swapping operation on NLI models to see the effectiveness of this straightforward method in mitigating the confounding factor problems in training generic sentence embeddings for other NLP transfer tasks.
Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent
While machine learning has achieved remarkable results in a wide variety of domains, the training of models often requires large datasets that may need to be collected from different individuals. As sensitive information may be contained in the individual’s dataset, sharing training data may lead to severe privacy concerns. One effective approach to build the privacy-aware machine learning methods is to leverage the generic framework of differential privacy. Considering that stochastic gradient descent (SGD) is one of the mostly adopted methods for large-scale machine learning problems, two decentralized differentially private SGD algorithms are proposed in this work. Particularly, we focus on SGD without replacement due to its favorable structure for practical implementation. In addition, both privacy and convergence analysis are provided for the proposed algorithms. Finally, extensive experiments are performed to verify the theoretical results and demonstrate the effectiveness of the proposed algorithms.
Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.
Instance-based Deep Transfer Learning
Deep transfer learning has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is arguably the most frequently used method. However, very little work has been devoted to enhancing deep transfer learning by focusing on the influence of data. In this work, we propose an instance-based approach to improve deep transfer learning in target domain. Specifically, we choose a pre-trained model which is learned from a source domain, and utilize this model to estimate the influence of each training sample in a target domain. Then we optimize training data of the target domain by removing the training samples that will lower the performance of the pre-trained model. We then fine-tune the pre-trained model with the optimized training data in the target domain, or build a new model which can be initialized partially based on the pre-trained model, and fine-tune it with the optimized training data in the target domain. Using this approach, transfer learning can help deep learning models to learn more useful features. Extensive experiments demonstrate the effectiveness of our approach on further boosting deep learning models for typical high-level computer vision tasks, such as image classification.
I Know What You Want: Semantic Learning for Text Comprehension
Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL). Although SRL is naturally essential to text comprehension tasks, it is surprisingly ignored in previous work. This paper thus makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal arguments and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by semantic role labels for more fine-grained semantics. We show that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Extensive experiments on benchmark machine reading comprehension and inference datasets verify that the proposed semantic learning helps our system reach new state-of-the-art.
Interpreting Neural Networks With Nearest Neighbors
Local model interpretation methods explain individual predictions by assigning an importance value to each input feature. This value is often determined by measuring the change in confidence when a feature is removed. However, the confidence of neural networks is not a robust measure of model uncertainty. This issue makes reliably judging the importance of the input features difficult. We address this by changing the test-time behavior of neural networks using Deep k-Nearest Neighbors. Without harming text classification accuracy, this algorithm provides a more robust uncertainty metric which we use to generate feature importance values. The resulting interpretations better align with human perception than baseline methods. Finally, we use our interpretation method to analyze model predictions on dataset annotation artifacts.
Identifying The Most Informative Features Using A Structurally Interacting Elastic Net
Feature selection can efficiently identify the most informative features with respect to the target feature used in training. However, state-of-the-art vector-based methods are unable to encapsulate the relationships between feature samples into the feature selection process, thus leading to significant information loss. To address this problem, we propose a new graph-based structurally interacting elastic net method for feature selection. Specifically, we commence by constructing feature graphs that can incorporate pairwise relationship between samples. With the feature graphs to hand, we propose a new information theoretic criterion to measure the joint relevance of different pairwise feature combinations with respect to the target feature graph representation. This measure is used to obtain a structural interaction matrix where the elements represent the proposed information theoretic measure between feature pairs. We then formulate a new optimization model through the combination of the structural interaction matrix and an elastic net regression model for the feature subset selection problem. This allows us to a) preserve the information of the original vectorial space, b) remedy the information loss of the original feature space caused by using graph representation, and c) promote a sparse solution and also encourage correlated features to be selected. Because the proposed optimization problem is non-convex, we develop an efficient alternating direction multiplier method (ADMM) to locate the optimal solutions. Extensive experiments on various datasets demonstrate the effectiveness of the proposed methods.
Online Adaptive Methods, Universality and Acceleration
We present a novel method for convex unconstrained optimization that, without any modifications, ensures: (i) accelerated convergence rate for smooth objectives, (ii) standard convergence rate in the general (non-smooth) setting, and (iii) standard convergence rate in the stochastic optimization setting. To the best of our knowledge, this is the first method that simultaneously applies to all of the above settings. At the heart of our method is an adaptive learning rate rule that employs importance weights, in the spirit of adaptive online learning algorithms (Duchi et al., 2011; Levy, 2017), combined with an update that linearly couples two sequences, in the spirit of (Allen-Zhu and Orecchia, 2017). An empirical examination of our method demonstrates its applicability to the above mentioned scenarios and corroborates our theoretical findings.
Modelling User’s Theory of AI’s Mind in Interactive Intelligent Systems
Many interactive intelligent systems, such as recommendation and information retrieval systems, treat users as a passive data source. Yet, users form mental models of systems and instead of passively providing feedback to the queries of the system, they will strategically plan their actions within the constraints of the mental model to steer the system and achieve their goals faster. We propose to explicitly account for the user’s theory of the AI’s mind in the user model: the intelligent system has a model of the user having a model of the intelligent system. We study a case where the system is a contextual bandit and the user model is a Markov decision process that plans based on a simpler model of the bandit. Inference in the model can be reduced to probabilistic inverse reinforcement learning, with the nested bandit model defining the transition dynamics, and is implemented using probabilistic programming. Our results show that improved performance is achieved if users can form accurate mental models that the system can capture, implying predictability of the interactive intelligent system is important not only for the user experience but also for the design of the system’s statistical models.
Towards Query Efficient Black-box Attacks: An Input-free Perspective
Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. However, most of the existing black-box attack algorithms need to make a huge amount of queries to perform attacks, which is not practical in the real world. We note one of the main reasons for the massive queries is that the adversarial example is required to be visually similar to the original image, but in many cases, how adversarial examples look like does not matter much. It inspires us to introduce a new attack called \emph{input-free} attack, under which an adversary can choose an arbitrary image to start with and is allowed to add perceptible perturbations on it. Following this approach, we propose two techniques to significantly reduce the query complexity. First, we initialize an adversarial example with a gray color image on which every pixel has roughly the same importance for the target model. Then we shrink the dimension of the attack space by perturbing a small region and tiling it to cover the input image. To make our algorithm more effective, we stabilize a projected gradient ascent algorithm with momentum, and also propose a heuristic approach for region size selection. Through extensive experiments, we show that with only 1,701 queries on average, we can perturb a gray image to any target class of ImageNet with a 100\% success rate on InceptionV3. Besides, our algorithm has successfully defeated two real-world systems, the Clarifai food detection API and the Baidu Animal Identification API.
Personalizing Fairness-aware Re-ranking
Personalized recommendation brings about novel challenges in ensuring fairness, especially in scenarios in which users are not the only stakeholders involved in the recommender system. For example, the system may want to ensure that items from different providers have a fair chance of being recommended. To solve this problem, we propose a Fairness-Aware Re-ranking algorithm (FAR) to balance the ranking quality and provider-side fairness. We iteratively generate the ranking list by trading off between accuracy and the coverage of the providers. Although fair treatment of providers is desirable, users may differ in their receptivity to the addition of this type of diversity. Therefore, personalized user tolerance towards provider diversification is incorporated. Experiments are conducted on both synthetic and real-world data. The results show that our proposed re-ranking algorithm can significantly promote fairness with a slight sacrifice in accuracy and can do so while being attentive to individual user differences.
Transforming Question Answering Datasets Into Natural Language Inference Datasets
Existing datasets for natural language inference (NLI) have propelled research on language understanding. We propose a new method for automatically deriving NLI datasets from the growing abundance of large-scale question answering datasets. Our approach hinges on learning a sentence transformation model which converts question-answer pairs into their declarative forms. Despite being primarily trained on a single QA dataset, we show that it can be successfully applied to a variety of other QA resources. Using this system, we automatically derive a new freely available dataset of over 500k NLI examples (QA-NLI), and show that it exhibits a wide range of inference phenomena rarely seen in previous NLI datasets.
MPS: An R package for modelling new families of distributions
| We introduce an \verb | R | package, called \verb | MPS | , for computing the probability density function, computing the cumulative distribution function, computing the quantile function, simulating random variables, and estimating the parameters of 24 new shifted families of distributions. By considering an extra shift (location) parameter for each family more flexibility yields. Under some situations, since the maximum likelihood estimators may fail to exist, we adopt the well-known maximum product spacings approach to estimate the parameters of shifted 24 new families of distributions. The performance of the \verb | MPS | package for computing the cdf, pdf, and simulating random samples will be checked by examples. The performance of the maximum product spacings approach is demonstrated by executing \verb | MPS | package for three sets of real data. As it will be shown, for the first set, the maximum likelihood estimators break down but \verb | MPS | package find them. For the second set, adding the location parameter leads to acceptance the model while absence of the location parameter makes the model quite inappropriate. For the third set, presence of the location parameter yields a better fit. |
Variational Approximation Accuracy in Bayesian Non-negative Matrix Factorization
Non-negative matrix factorization (NMF) is a knowledge discovery method that is used for many fields, besides, its variational inference and Gibbs sampling method are also well-known. However, the variational approximation accuracy is not yet clarified, since NMF is not statistically regular and the prior used in the variational Bayesian NMF (VBNMF) has zero or divergence points. In this paper, using algebraic geometrical methods, we theoretically analyze the difference of the negative log evidence/marginal likelihood (free energy) between VBNMF and Bayesian NMF, and give a lower bound of the approximation accuracy, asymptotically. The results quantitatively show how well the VBNMF algorithm can approximate Bayesian NMF.
• New ECG Delineation Database• Generalized Ait-Sahalia-type interest rate model with Poisson jumps and convergence of the numerical approximation• Landslide Monitoring based on Terrestrial Laser Scanning: A Novel Semi-automatic Workflow• Insider Threat Detection Through Attributed Graph Clustering• A Comparison of Handcrafted and Deep Neural Network Feature Extraction for Classifying Optical Coherence Tomography (OCT) Images• MANTIS: Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR T2 mapping• Fake Cures: User-centric Modeling of Health Misinformation in Social Media• A Global Alignment Kernel based Approach for Group-level Happiness Intensity Estimation• Hierarchical Video Understanding• A Robotic Auto-Focus System based on Deep Reinforcement Learning• YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark• Guiding the Creation of Deep Learning-based Object Detectors• A Stable Minutia Descriptor based on Gabor Wavelet and Linear Discriminant Analysis• Another method of viscosity solutions of integro-differential partial equation by concavity• GANs for generating EFT models• Deriving Enhanced Geographical Representations via Similarity-based Spectral Analysis: Predicting Colorectal Cancer Survival Curves in Iowa• Network Topology Mapping from Partial Virtual Coordinates and Graph Geodesics• Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control• Centralized and distributed schedulers for non-coherent joint transmission• Neural Allocentric Intuitive Physics Prediction from Real Videos• Revisiting Inaccuracies of Time Series Averaging under Dynamic Time Warping• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders• Pushing the Limits of Encrypted Databases with Secure Hardware• Parameterized algorithm for 3-path vertex cover• Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features• Intriguing sets in distance regular graphs• Hyperuniform point sets on the sphere: probabilistic aspects• Minimally Constrained Stable Switched Systems and Application to Co-simulation• Reservoir Computing based Neural Image Filters• Complexity of MLDP• A general-purpose hierarchical mesh partitioning method with node balancing strategies for large-scale numerical simulations• Unsupervised Sentence Compression using Denoising Auto-Encoders• RetGK: Graph Kernels based on Return Probabilities of Random Walks• Migration as Submodular Optimization• Multi-branched left-sided multifractality and phase transitions in time series of interevent times• When Hashing Met Matching: Efficient Search for Potential Matches in Ride Sharing• Distinct Partial Sums in Cyclic Groups: Polynomial Method and Constructive Approaches• Marking and shifting a part in partition theorems• Multiresolution analysis and adaptive estimation on a sphere using stereographic wavelets Bogdan Ćmiel• Dynamic Resource Allocation in the Cloud with Near-Optimal Efficiency• Selective Refinement Network for High Performance Face Detection• Neural Machine Translation of Logographic Languages Using Sub-character Level Information• Global Universality of Macdonald Plane Partitions• Maximum Correntropy Derivative-Free Robust Kalman Filter and Smoother• Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions• Torpid Mixing of Markov Chains for the Six-vertex Model on $\mathbb{Z}^2$• Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms• Adaptive Edge Features Guided Graph Attention Networks• BLAG: Bandit On Large Action Set Graph• DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking• On Coding over Sliced Information• Cost Sharing in Two-Sided Markets• Learning to Solve NP-Complete Problems – A Graph Neural Network for the Decision TSP• Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data• Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning• Joint Autoregressive and Hierarchical Priors for Learned Image Compression• A strategy for solving difficulties in spin-glass simulations• Ensembles of Nested Dichotomies with Multiple Subset Evaluation• A high dimensional Central Limit Theorem for martingales, with applications to context tree models• RealPoint3D: Point Cloud Generation from a Single Image with Complex Background• On the Calibration of Nested Dichotomies for Large Multiclass Tasks• Molecular Hypergraph Grammar with its Application to Molecular Optimization• Ultimate Boundedness for Switched Systems with Multiple Equilibria Under Disturbances• Optimal and Low-Complexity Dynamic Spectrum Access for RF-Powered Ambient Backscatter System with Online Reinforcement Learning• A Game Theoretic Macroscopic Model of Bypassing at Traffic Diverges with Applications to Mixed Autonomy Networks• Exploration on Grounded Word Embedding: Matching Words and Images with Image-Enhanced Skip-Gram Model• CNNs for Surveillance Footage Scene Classification• Generating Distractors for Reading Comprehension Questions from Real Examinations• Hybrid Statistical Estimation of Mutual Information and its Application to Information Flow• Weak Control for Human-in-the-loop Systems• Order book model with herd behavior exhibiting long-range memory• Resumption of dynamism in damaged networks of coupled oscillators• Capacity analysis and bit allocation design for variable-resolution ADCs in Massive MIMO• Improving Wireless Physical Layer Security via D2D Communication• Sentiment analysis for Arabic language: A brief survey of approaches and techniques• On a nonlinear neutral stochastic functional integro-differential equation driven by fractional Brownian motion• Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples• Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering• Simplified Hierarchical Recurrent Encoder-Decoder for Building End-To-End Dialogue Systems• Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution• Fully-Functional Suffix Trees and Optimal Text Searching in BWT-runs Bounded Space• Attentive Semantic Role Labeling with Boundary Indicator• Fast Gradient Attack on Network Embedding• A note on the edge partition of graphs containing either a light edge or an alternating 2-cycle• Video Smoke Detection Based on Deep Saliency Network• Determinstic and stochastic 2d Navier-Stokes equations with anisotropic viscosity• Handling Concept Drift via Model Reuse• Faithful Multimodal Explanation for Visual Question Answering• The Birkhoff Diamond as Double Agent• A conjecture on permutation trinomials over finite fields of characteristic two• Multi-label Classification of User Reactions in Online News• Mixing conditions of conjugate processes• Extracting and Analyzing Semantic Relatedness between Cities Using News Articles• A natural language processing and geospatial clustering framework for harvesting local place names from geotagged housing advertisements• Performance Analysis of a System with Bursty Traffic and Adjustable Transmission Times• Multitasking Capacity: Hardness Results and Improved Constructions• Context-Free Transductions with Neural Stacks• Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes• Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform• Neural Guided Constraint Logic Programming for Program Synthesis• Resolution and the binary encoding of combinatorial principles• Rate-Adaptive Neural Networks for Spatial Multiplexers• Online Mutual Foreground Segmentation for Multispectral Stereo Videos• Asymptotic law of a modified score statistic for the asymmetric power distribution with unknown location and scale parameters• Learning Sports Camera Selection from Internet Videos• iDriveSense: Dynamic Route Planning Involving Roads Quality Information• Computational Sufficiency, Reflection Groups, and Generalized Lasso Penalties• Application of EOS-ELM with binary Jaya-based feature selection to real-time transient stability assessment using PMU data• On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks• A survey of food recommenderson• A Review on Cooperative Adaptive Cruise Control (CACC) Systems: Architectures, Controls, and Applications• Unsupervised Person Re-identification by Deep Learning Tracklet Association• A Supervised Learning Methodology for Real-Time Disguised Face Recognition in the Wild• Real-time control of metro train dynamics with minimization of train time-headway variance• PhaseLink: A Deep Learning Approach to Seismic Phase Association• Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection• Lost in the Digital Wild: Hiding Information in Digital Activities• Directional Frame Timing Synchronization in Wideband Millimeter-Wave Systems with Low-Resolution ADCs• Outage Probability Analysis of Uplink NOMA over Ultra-High-Speed FSO-Backhauled Systems• Apparent slow dynamics in the ergodic phase of a driven many-body localized system without extensive conserved quantities• A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking• End-to-end Language Identification using NetFV and NetVLAD• Alon-Tarsi number of signed planar graphs• On higher level Kirillov–Reshetikhin crystals, Demazure crystals, and related uniform models• Elliptical Distributions-Based Weights-Determining Method for OWA Operators• Synthesis of Different Autonomous Vehicles Test Approaches• Communication-Efficient Distributed Strongly Convex Stochastic Optimization: Non-Asymptotic Rates• Comparison-Based Algorithms for One-Dimensional Stochastic Convex Optimization• Factorisation of Greedoid Polynomials of Rooted Digraphs• Addressing Sample Inefficiency and Reward Bias in Inverse Reinforcement Learning• Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning• Generic Probabilistic Interactive Situation Recognition and Prediction: From Virtual to Real• Topology Adaption for the Quantum Internet• From Recommendation Systems to Facility Location Games• Reinforcement Learning for Decentralized Trajectory Design in Cellular UAV Networks with Sense-and-Send Protocol• Combining tumour response and progression free survival as surrogate endpoints for overall survival in advanced colorectal cancer• Efficient and Robust Recovery of Signal and Image in Impulsive Noise via $\ell_1-α\ell_2$ Minimization• Automated Strabismus Detection based on Deep neural networks for Telemedicine Applications• Cellular automata as convolutional neural networks• Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information• Non-coherent Massive SIMO Systems in ISI Channels: Constellation Design and Performance Analysis• Data scraping, ingestation, and modeling: bringing data from cars.com into the intro stats class• Full vs. no information best choice game with finite horizon• Laplacian Simplices II: A Coding Theoretic Approach• Strong Coresets for k-Median and Subspace Approximation: Goodbye Dimension• Quantum Hamiltonian Identifiability via a Similarity Transformation Approach and Beyond• LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo• Geometry-Aware Face Completion and Editing• Nonparametric semisupervised classification for signal detection in high energy physics• Time-universal data compression and prediction• Age of Information in Poisson Networks• Dual Attention Network for Scene Segmentation• On zero-sum game formulation of non zero-sum game• Speeding Up Neural Machine Translation Decoding by Cube Pruning
Like this:
Like Loading…
Related