Solving for multi-class: a survey and synthesis
We review common methods of solving for multi-class from binary and generalize them to a common framework. Since conditional probabilties are useful both for quantifying the accuracy of an estimate and for calibration purposes, these are a required part of the solution. There is some indication that the best solution for multi-class classification is dependent on the particular dataset. As such, we are particularly interested in data-driven solution design, whether based on a priori considerations or empirical examination of the data. Numerical results indicate that while a one-size-fits-all solution consisting of one-versus-one is appropriate for most datasets, a minority will benefit from a more customized approach. The techniques discussed in this paper allow for a large variety of multi-class configurations and solution methods to be explored so as to optimize classification accuracy, accuracy of conditional probabilities and speed.
Maximum-Entropy Fine-Grained Classification
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data. Utilizing this notion of small visual diversity, we revisit Maximum-Entropy learning in the context of fine-grained classification, and provide a training routine that maximizes the entropy of the output probability distribution for training convolutional neural networks on FGVC tasks. We provide a theoretical as well as empirical justification of our approach, and achieve state-of-the-art performance across a variety of classification tasks in FGVC, that can potentially be extended to any fine-tuning task. Our method is robust to different hyperparameter values, amount of training data and amount of training label noise and can hence be a valuable tool in many similar problems.
Bayesian Modular and Multiscale Regression
A Deep Generative Model for Semi-Supervised Classification with Noisy Labels
Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for label noise. Additionally, the derivation of M-VAE gives new theoretical insights into the popular M1+M2 semi-supervised model.
Robust Adversarial Perturbation on Deep Proposal-based Models
Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and instance segmentation algorithms. Our method focuses on attacking the common component in these algorithms, namely Region Proposal Network (RPN), to universally degrade their performance in a black-box fashion. To do so, we design a loss function that combines a label loss and a novel shape loss, and optimize it with respect to image using a gradient based iterative algorithm. Evaluations are performed on the MS COCO 2014 dataset for the adversarial attacking of 6 state-of-the-art object detectors and 2 instance segmentation algorithms. Experimental results demonstrate the efficacy of the proposed method.
Latent Space Optimal Transport for Generative Models
Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which can be important for datasets such as facial images. A GAN can transform a simple distribution to a latent-space data distribution and thus preserve the manifold structure, but optimizing a GAN involves solving a Min-Max optimization problem, which is difficult and not well understood so far. Therefore, we propose a GAN-like method to transform a simple distribution to a data distribution in the latent space by solving only a minimization problem. This minimization problem comes from training a discriminator between a simple distribution and a latent-space data distribution. Then, we can explicitly formulate an Optimal Transport (OT) problem that computes the desired mapping between the two distributions. This means that we can transform a distribution without solving the difficult Min-Max optimization problem. Experimental results on an eight-Gaussian dataset show that the proposed OT can handle multi-cluster distributions. Results on the MNIST and the CelebA datasets validate the effectiveness of the proposed method.
The Structure of the Realizations of the Causal Information Rate-Distortion Function for Markovian Sources: Realizations with Densities
FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis
The tremendous potential exhibited by deep learning is often offset by architectural and computational complexity, making widespread deployment a challenge for edge scenarios such as mobile and other consumer devices. To tackle this challenge, we explore the following idea: Can we learn generative machines to automatically generate deep neural networks with efficient network architectures? In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements. What is most interesting is that, once a generator has been learned through generative synthesis, it can be used to generate not just one but a large variety of different, unique highly efficient deep neural networks that satisfy operational requirements. Experimental results for image classification, semantic segmentation, and object detection tasks illustrate the efficacy of generative synthesis in producing generators that automatically generate highly efficient deep neural networks (which we nickname FermiNets) with higher model efficiency and lower computational costs (reaching >10x more efficient and fewer multiply-accumulate operations than several tested state-of-the-art networks), as well as higher energy efficiency (reaching >4x improvements in image inferences per joule consumed on a Nvidia Tegra X2 mobile processor). As such, generative synthesis can be a powerful, generalized approach for accelerating and improving the building of deep neural networks for on-device edge scenarios.
Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization
Clustering with incomplete views is a challenge in multi-view clustering. In this paper, we provide a novel and simple method to address this issue. Specifically, the proposed method simultaneously exploits the local information of each view and the complementary information among views to learn the common latent representation for all samples, which can greatly improve the compactness and discriminability of the obtained representation. Compared with the conventional graph embedding methods, the proposed method does not introduce any extra regularization term and corresponding penalty parameter to preserve the local structure of data, and thus does not increase the burden of extra parameter selection. By imposing the orthogonal constraint on the basis matrix of each view, the proposed method is able to handle the out-of-sample. Moreover, the proposed method can be viewed as a unified framework for multi-view learning since it can handle both incomplete and complete multi-view clustering and classification tasks. Extensive experiments conducted on several multi-view datasets prove that the proposed method can significantly improve the clustering performance.
Learning to Accept New Classes without Training
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such an environment must be able to reject unseen classes (not seen or used in training). If enough data is collected for the unseen classes, the system should incrementally learn to accept/classify them. This learning paradigm is called open-world learning (OWL). Existing OWL methods all need some form of re-training to accept or include the new classes in the overall model. In this paper, we propose a meta-learning approach to the problem. Its key novelty is that it only needs to train a meta-classifier, which can then continually accept new classes when they have enough labeled data for the meta-classifier to use, and also detect/reject future unseen classes. No re-training of the meta-classifier or a new overall classifier covering all old and new classes is needed. In testing, the method only uses the examples of the seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results demonstrate the effectiveness of the new approach.
Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression
In this paper, we propose a random projection approach to estimate variance in kernel ridge regression. Our approach leads to a consistent estimator of the true variance, while being computationally more efficient. Our variance estimator is optimal for a large family of kernels, including cubic splines and Gaussian kernels. Simulation analysis is conducted to support our theory.
Understanding and forecasting lifecycle events in information cascades
Most social network sites allow users to reshare a piece of information posted by a user. As time progresses, the cascade of reshares grows, eventually saturating after a certain time period. While previous studies have focused heavily on one aspect of the cascade phenomenon, specifically predicting when the cascade would go viral, in this paper, we take a more holistic approach by analyzing the occurrence of two events within the cascade lifecycle – the period of maximum growth in terms of surge in reshares and the period where the cascade starts declining in adoption. We address the challenges in identifying these periods and then proceed to make a comparative analysis of these periods from the perspective of network topology. We study the effect of several node-centric structural measures on the reshare responses using Granger causality which helps us quantify the significance of the network measures and understand the extent to which the network topology impacts the growth dynamics. This evaluation is performed on a dataset of 7407 cascades extracted from the Weibo social network. Using our causality framework, we found that an entropy measure based on nodal degree causally affects the occurrence of these events in 93.95% of cascades. Surprisingly, this outperformed clustering coefficient and PageRank which we hypothesized would be more indicative of the growth dynamics based on earlier studies. We also extend the Granger-causality Vector Autoregression (VAR) model to forecast the times at which the events occur in the cascade lifecycle.
Implementable Quantum Classifier for Nonlinear Data
Transparency and Explanation in Deep Reinforcement Learning Neural Networks
Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i.e. the system should be transparent. System transparency enables humans to form coherent explanations of the system’s decisions and actions. Transparency is important not only for user trust, but also for software debugging and certification. In recent years, Deep Neural Networks have made great advances in multiple application areas. However, deep neural networks are opaque. In this paper, we report on work in transparency in Deep Reinforcement Learning Networks (DRLN). Such networks have been extremely successful in accurately learning action control in image input domains, such as Atari games. In this paper, we propose a novel and general method that (a) incorporates explicit object recognition processing into deep reinforcement learning models, (b) forms the basis for the development of ‘object saliency maps’, to provide visualization of internal states of DRLNs, thus enabling the formation of explanations and (c) can be incorporated in any existing deep reinforcement learning framework. We present computational results and human experiments to evaluate our approach.
Testing relevant hypotheses in functional time series via self-normalization
The Serverless Scheduling Problem and NOAH
The serverless scheduling problem poses a new challenge to Cloud service platform providers because it is rather a job scheduling problem than a traditional resource allocation or request load balancing problem. Traditionally, elastic cloud applications use managed virtual resource allocation and employ request load balancers to orchestrate the deployment. With serverless, the provider needs to solve both the load balancing and the allocation. This work reviews the current Apache OpenWhisk serverless event load balancing and a noncooperative game-theoretic load balancing approach for response time minimization in distributed systems. It is shown by simulation that neither performs well under high system utilization which inspired a noncooperative online allocation heuristic that allows tuning the trade-off between for response time and resource cost of each serverless function.
Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification problems. As logistic regression is widely known not having a closed-form solution, it is usually randomly initialized, leading to several deficiencies especially in transfer learning where all the layers except for the last task-specific layer are initialized using a pre-trained model. The deficiencies include slow convergence speed, possibility of stuck in local minimum, and the risk of over-fitting. To address those deficiencies, we first study the properties of logistic regression and propose a closed-form approximate solution named regularized Gaussian classifier (RGC). Then we adopt this approximate solution to initialize the task-specific linear layer and demonstrate superior performance over random initialization in terms of both accuracy and convergence speed on various tasks and datasets. For example, for image classification, our approach can reduce the training time by 10 times and achieve 3.2% gain in accuracy for Flickr-style classification. For object detection, our approach can also be 10 times faster in training for the same accuracy, or 5% better in terms of mAP for VOC 2007 with slightly longer training.
Heteroskedasticity-robust inference in linear regression models
This paper considers inference in heteroskedastic linear regression models with many control variables. The slope coefficients on these variables are nuisance parameters. Our setting allows their number to grow with the sample size, possibly at the same rate, in which case they are not consistently estimable. A prime example of this setting are models with many (possibly multi-way) fixed effects. The presence of many nuisance parameters introduces an incidental-parameter problem in the usual heteroskedasticity-robust estimators of the covariance matrix, rendering them biased and inconsistent. Hence, tests based on these estimators are size distorted even in large samples. An alternative covariance-matrix estimator that is conditionally unbiased and remains consistent is presented and supporting simulation results are provided.
Convex Formulation for Regularized Estimation of Structural Equation Models
Path analysis is a special class of models in structural equation modeling (SEM) where it describes causal relations among measured variables in a form of linear regression. This paper presents two estimation formulations for confirmatory and exploratory SEM in path analysis problems where a zero pattern of the estimated path coefficient matrix explains a causality structure of the variables. In confirmatory SEM, the original nonlinear equality constraints of model parameters are relaxed to an inequality, allowing us to transform the original problem into a convex problem. A regularized estimation formulation is proposed for exploratory SEM, where the objective function is added with an l1-type penalty of the path coefficient matrix. Under a condition on problem parameters, we show that our optimal solution is low rank and provides an estimate of the path matrix of the original problem. To solve our estimation problems in a convex framework, we apply alternating direction method of multiplier (ADMM) which is shown to be suitable for a large-scale implementation. In combination with applying model selection criteria, the penalty parameter in the regularized estimation, controlling the density of nonzero entries in the path matrix, can be chosen to provide a reasonable trade-off between the model fitting and the complexity of causality structure. The performance of our approach is demonstrated in both simulated and real data sets, and with a comparison of existing methods. Real application results include learning causality among climate variables in Thailand where our findings can explain known relations among air pollutants and weather variables. The other experiment is to explore connectivities among brain regions using fMRI time series from ABIDE data sets where our results are interpreted to explain brain network differences in autism patients.
Probabilistic DL Reasoning with Pinpointing Formulas: A Prolog-based Approach
ADBSCAN: Adaptive Density-Based Spatial Clustering of Applications with Noise for Identifying Clusters with Varying Densities
Density-based spatial clustering of applications with noise (DBSCAN) is a data clustering algorithm which has the high-performance rate for dataset where clusters have the constant density of data points. One of the significant attributes of this algorithm is noise cancellation. However, DBSCAN demonstrates reduced performances for clusters with different densities. Therefore, in this paper, an adaptive DBSCAN is proposed which can work significantly well for identifying clusters with varying densities.
A Network Topology Approach to Bot Classification
Automated social agents, or bots, are increasingly becoming a problem on social media platforms. There is a growing body of literature and multiple tools to aid in the detection of such agents on online social networking platforms. We propose that the social network topology of a user would be sufficient to determine whether the user is a automated agent or a human. To test this, we use a publicly available dataset containing users on Twitter labelled as either automated social agent or human. Using an unsupervised machine learning approach, we obtain a detection accuracy rate of 70%.
The Fast and the Flexible: training neural networks to learn to follow instructions from small data
Learning to follow human instructions is a challenging task because while interpreting instructions requires discovering arbitrary algorithms, humans typically provide very few examples to learn from. For learning from this data to be possible, strong inductive biases are necessary. Work in the past has relied on hand-coded components or manually engineered features to provide such biases. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively.
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims to improve the overall performance of several ranking strategies in different scenarios, is rather untouched. Separately optimizing each individual strategy has two limitations. The first one is lack of collaboration between scenarios meaning that each strategy maximizes its own objective but ignores the goals of other strategies, leading to a sub-optimal overall performance. The second limitation is the inability of modeling the correlation between scenarios meaning that independent optimization in one scenario only uses its own user data but ignores the context in other scenarios. In this paper, we formulate multi-scenario ranking as a fully cooperative, partially observable, multi-agent sequential decision problem. We propose a novel model named Multi-Agent Recurrent Deterministic Policy Gradient (MA-RDPG) which has a communication component for passing messages, several private actors (agents) for making actions for ranking, and a centralized critic for evaluating the overall performance of the co-working actors. Each scenario is treated as an agent (actor). Agents collaborate with each other by sharing a global action-value function (the critic) and passing messages that encodes historical information across scenarios. The model is evaluated with online settings on a large E-commerce platform. Results show that the proposed model exhibits significant improvements against baselines in terms of the overall performance.
Nested Performance Profiles for Benchmarking Software
In order to compare and benchmark the mathematical software, the performance profiles have been introduced [1]. However, it has been proved that the algorithm is not flawless. The main issue with the performance profile is that it may rank the solvers with respect to the best solver, by excluding the best one and running the algorithm on the remaining set of the solvers, the method may rank the solvers in a different way. We characterize such systems of problems-solvers and propose an efficient and reliable algorithm to overcome this negative side effect. The proposed method is unbiased in comparing the solvers and is successful in detecting the top ones
Adversarial Text Generation via Feature-Mover’s Distance
Generative adversarial networks (GANs) have achieved significant success in generating real-valued data. However, the discrete nature of text hinders the application of GAN to text-generation tasks. Instead of using the standard GAN objective, we propose to improve text-generation GAN via a novel approach inspired by optimal transport. Specifically, we consider matching the latent feature distributions of real and synthetic sentences using a novel metric, termed the feature-mover’s distance (FMD). This formulation leads to a highly discriminative critic and easy-to-optimize objective, overcoming the mode-collapsing and brittle-training problems in existing methods. Extensive experiments are conducted on a variety of tasks to evaluate the proposed model empirically, including unconditional text generation, style transfer from non-parallel text, and unsupervised cipher cracking. The proposed model yields superior performance, demonstrating wide applicability and effectiveness.
Automata Guided Reinforcement Learning With Demonstrations
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We propose to address these problems by combining temporal logic (TL) with reinforcement learning from demonstrations. Our method automatically generates intrinsic rewards that align with the overall task goal given a TL task specification. The policy resulting from our framework has an interpretable and hierarchical structure. We validate the proposed method experimentally on a set of robotic manipulation tasks.
Scalable network adaptation for Cloud-RANs: An imitation learning approach
Network adaptation is essential for the efficient operation of Cloud-RANs. Unfortunately, it leads to highly intractable mixed-integer nonlinear programming problems. Existing solutions typically rely on convex relaxation, which yield performance gaps that are difficult to quantify. Meanwhile, global optimization algorithms such as branch-and-bound can find optimal solutions but with prohibitive computational complexity. In this paper, to obtain near-optimal solutions at affordable complexity, we propose to approximate the branch-and-bound algorithm via machine learning. Specifically, the pruning procedure in branch-and-bound is formulated as a sequential decision problem, followed by learning the oracle’s action via imitation learning. A unique advantage of this framework is that the training process only requires a small dataset, and it is scalable to problem instances with larger dimensions than the training setting. This is achieved by identifying and leveraging the problem-size independent features. Numerical simulations demonstrate that the learning based framework significantly outperforms competing methods, with computational complexity much lower than the traditional branch-and-bound algorithm.
• Quantum Money from Modular Forms• On analyzing and evaluating privacy measures for social networks under active attack• Crump-Mode-Jagers Processes with Immigration and Their Scaling Limits (I): Light-tailed Case• A #SAT Algorithm for Small Constant-Depth Circuits with PTF gates• Day-to-day dynamic traffic assignment model with variable message signs and endogenous user compliance• Breast Cancer Detection through Electrical Impedance Tomography and Optimal Control Theory: Theoretical and Computational Analysis• Minimal Realization Problems for Jump Linear Systems• The Space-Efficient Core of Vadalog• Parameters estimation in a 3-parameters p-star model• Performance Analysis of Molecular Spatial Modulation (MSM) in Diffusion based Molecular MIMO Communication Systems• 3D Path Planning from a Single 2D Fluoroscopic Image for Robot Assisted Fenestrated Endovascular Aortic Repair• A Distributed Learning Architecture for Scientific Imaging Problems• Lazy Modeling of Variants of Token Swapping Problem and Multi-agent Path Finding through Combination of Satisfiability Modulo Theories and Conflict-based Search• Support theorem for an SPDE with multiplicative noise driven by a cylindrical Wiener process on the real line• Attacking Object Detectors via Imperceptible Patches on Background• Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization• Finitely forcible graphons with an almost arbitrary structure• The extremal function for $K_9^=$ minors• Graphs with no $K_9^=$ minor are 10-colorable• Semiparametric fractional imputation using Gaussian mixture models for handling multivariate missing data• Observation and Distinction. Representing Information in Infinite Games• A proximal ALM method for computing Wasserstein barycenter in D2-clustering of discrete distributions• Highly-Economized Multi-View Binary Compression for Scalable Image Clustering• Approximate super-resolution and truncated moment problems in all dimensions• Devil in the Details: Towards Accurate Single and Multiple Human Parsing• General formation control for multi-agent systems with double-integrator dynamics• Fast Maximum Power Point Tracking for PV Arrays under Partial shaded Conditions• Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection• Distributed Subgradient Method for Convex Constrained Optimization: Non-ergodic Convergence Guarantees• Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering• DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation• Doppler Spectrum Analysis of a Roadside Scatterer Model for Vehicle-to-Vehicle Channels: An Indirect Method• The Impact of On-chip Communication on Memory Technologies for Neuromorphic Systems• Integrative Analysis of Patient Health Records and Neuroimages via Memory-based GraphConvolutional Network• Authentication of cyber-physical systems under learning-based attacks• A convex formulation for high-dimensional sparse sliced inverse regression• Autonomous Exploration, Reconstruction, and Surveillance of 3D Environments Aided by Deep Learning• BSE: A Minimal Simulation of a Limit-Order-Book Stock Exchange• A Lower Lower-Critical Spin-Glass Dimension from Quenched Mixed-Spatial-Dimensional Spin Glasses• Hybrid Block Diagonalization for Massive MIMO Two-Way Half-Duplex AF Hybrid Relay• New Reconfigurable L-Band Digital Aeronautical Communication System• Extracting Universal Representations of Cognition across Brain-Imaging Studies• Binocular Tone Mapping with Improved Overall Contrast and Local Details• On tails of exit times of multidimensional Lévy processes• Multi-Player Bandits: A Trekking Approach• Equivalence between pathbreadth and strong pathbreadth• Path Integral Approach to Random Neural Networks• Building Prior Knowledge: A Markov Based Pedestrian Prediction Model Using Urban Environmental Data• Erratic Extremism causes Dynamic Consensus (a new model for one-dimensional opinion dynamics)• Parameter Estimation of absolute continuous four parameter Geometric Marshall-Olkin bivariate Pareto Distribution• Cumulative effects of triadic closure and homophily in social networks• Model-Driven Deep Learning for Physical Layer Communications• Contact Adaption during Epidemics: A Multilayer Network Formulation Approach• Risk-Averse Model Predictive Operation Control of Islanded Microgrids• Object-sensitive Deep Reinforcement Learning• Focal Loss in 3D Object Detection• Energy cost for controlling complex networks• Bismut Formula for Lions Derivative of Distribution Dependent SDEs and Applications• Seuillage par hystérésis pour le test de photo-consistance des voxels dans le cadre de la reconstruction 3D• Modeling Nelson-Siegel Yield Curve using Bayesian Approach• An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge• Similarity measure for Public Persons• Infinite classes of strongly regular graphs derived from $GL(n,F_2)$• Proofs and Reductions of Kanade and Russell’s partition identities• Policy Optimization via Importance Sampling• On Minimal Copulas under the Concordance Orde• DeepEfficiency – optimal efficiency inversion in higher dimensions at the LHC• A solution for stochastic games• Merge Non-Dominated Sorting Algorithm for Many-Objective Optimization• Hamiltonicity in Convex Bipartite Graphs• Matrix Completion with Weighted Constraint for Haplotype Estimation• cf2vec: Collaborative Filtering algorithm selection using graph distributed representations• Muscle Excitation Estimation in Biomechanical Simulation Using NAF Reinforcement Learning• Limit shape of minimal difference partitions and fractional statistics• Span error bound for weighted SVM with applications in hyperparameter selection• Globally Optimal AC Power System Upgrade Planning under Operational Policy Constraints• DeepDrum: An Adaptive Conditional Neural Network• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration• An Argument Communication Model of Polarization and Ideological Alignment• Automatic Electrodes Detection during simultaneous EEG/fMRI acquisition• On the Reconstruction of Static and Dynamic Discrete Structures• Open Subtitles Paraphrase Corpus for Six Languages• Contribution to the discussion of ‘When should meta-analysis avoid making hidden normality assumptions?’: A Bayesian perspective• Curriculum goal masking for continuous deep reinforcement learning• Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation• Dynamics Estimation Using Recurrent Neural Network• Categorization of Comparative Sentences for Argument Mining• Long-time trajectorial large deviations for affine stochastic volatility models and application to variance reduction for option pricing• Periocular Recognition Using CNN Features Off-the-Shelf• Equitable Partition Theorem of Tensors and Spectrum of Generalized Power Hypergraphs• Power Systems Topology and State Estimation by Graph Blind Source Separation• Graph Neural Networks for IceCube Signal Classification• Best-case and Worst-case Sparsifiability of Boolean CSPs• The Importance of Being Earnest: Performance of Modulation Classification for Real RF Signals• Learning of Multi-Context Models for Autonomous Underwater Vehicles• Dual Dense Encoding for Zero-Example Video Retrieval• Deploying South African Social Honeypots on Twitter• Study and Observation of the Variation of Accuracies of KNN, SVM, LMNN, ENN Algorithms on Eleven Different Datasets from UCI Machine Learning Repository• Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network• Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Neural Network Algorithm• Multi Modal Convolutional Neural Networks forBrain Tumor Segmentation• Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing• From Same Photo: Cheating on Visual Kinship Challenges• Quantum Statistics-Inspired Neural Attention• Unicyclic signed graphs with maximal energy• Unsupervised Sense-Aware Hypernymy Extraction• Explicit multiobjective model predictive control for nonlinear systems with symmetries• $C^{3}LES$: Codes for Coded Computation that Leverage Stragglers• An inertial extrapolation method for convex simple bilevel optimization• Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation• Industrial Smoke Detection and Visualization• Rank-based approach for estimating correlations in mixed ordinal data• A Strongly Polynomial Algorithm for Linear Exchange Markets• Learning Effective RGB-D Representations for Scene Recognition• Low-degree planar polynomials over finite fields of characteristic two• Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs• Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate• Style Transfer Through Multilingual and Feedback-Based Back-Translation• Mapping structural diversity in networks sharing a given degree distribution and global clustering: Adaptive resolution grid search evolution with Diophantine equation-based mutations• What increases (social) media attention: Research impact, author prominence or title attractiveness?• Approximate message-passing for convex optimization with non-separable penalties• Commonsense for Generative Multi-Hop Question Answering Tasks• Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation• On the geometry of strongly flat semigroups and their generalizations• ‘FabSearch’ : A 3D CAD Model Based Search Engine for Sourcing Manufacturing Services• Synchronization of Kuramoto oscillators in a bidirectional frequency-dependent tree network• Diffusive MIMO Molecular Communications: Channel Estimation, Equalization and Detection• Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks• Hypergraph expanders of all uniformities from Cayley graphs• Tracking Position and Orientation through Millimeter Wave Lens MIMO in 5G Systems• Persistent Coverage Control for Teams of Heterogeneous Agents – Extended Version• Satisfiability Bounds for ω-regular Properties in Interval-valued Markov Chains• Apple Flower Detection using Deep Convolutional Networks• The Parallelization of Riccati Recursion• Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning
Like this:
Like Loading…
Related