Making BREAD: Biomimetic strategies for Artificial Intelligence Now and in the Future
The Artificial Intelligence (AI) revolution foretold of during the 1960s is well underway in the second decade of the 21st century. Its period of phenomenal growth likely lies ahead. Still, we believe, there are crucial lessons that biology can offer that will enable a prosperous future for AI. For machines in general, and for AI’s especially, operating over extended periods or in extreme environments will require energy usage orders of magnitudes more efficient than exists today. In many operational environments, energy sources will be constrained. Any plans for AI devices operating in a challenging environment must begin with the question of how they are powered, where fuel is located, how energy is stored and made available to the machine, and how long the machine can operate on specific energy units. Hence, the materials and technologies that provide the needed energy represent a critical challenge towards future use-scenarios of AI and should be integrated into their design. Here we make four recommendations for stakeholders and especially decision makers to facilitate a successful trajectory for this technology. First, that scientific societies and governments coordinate Biomimetic Research for Energy-efficient, AI Designs (BREAD); a multinational initiative and a funding strategy for investments in the future integrated design of energetics into AI. Second, that biomimetic energetic solutions be central to design consideration for future AI. Third, that a pre-competitive space be organized between stakeholder partners and fourth, that a trainee pipeline be established to ensure the human capital required for success in this area.
EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search
E-commerce sponsored search contributes an important part of revenue for the e-commerce company. In consideration of effectiveness and efficiency, a large-scale sponsored search system commonly adopts a multi-stage architecture. We name these stages as \textit{ad retrieval}, \textit{ad pre-ranking} and \textit{ad ranking}. \textit{Ad retrieval} and \textit{ad pre-ranking} are collectively referred to as \textit{ad matching} in this paper. We propose an end-to-end neural matching framework (EENMF) to model two tasks—\textit{vector-based ad retrieval} and \textit{neural networks based ad pre-ranking}. Under the deep \textit{matching} framework, \textit{vector-based ad retrieval} harnesses user recent behavior sequence to retrieve relevant ad candidates without the constraint of keyword bidding. Simultaneously, the deep model is employed to perform the global pre-ranking of ad candidates from multiple retrieval paths effectively and efficiently. Besides, the proposed model tries to optimize the pointwise cross-entropy loss which is consistent with the objective of predict models in the ranking stage. We conduct extensive evaluation to validate the performance of the proposed framework. In the real traffic of a large-scale e-commerce sponsored search, the proposed approach significantly outperforms the baseline.
Learning to Fuse Things and Stuff
We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.
e-SNLI: Natural Language Inference withNatural Language Explanations
In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time. In this work, we extend the Stanford Natural Language Inference dataset with an additional layer of human-annotated natural language explanations of the entailment relations. We further implement models that incorporate these explanations into their training process and output them at test time. We show how our corpus of explanations, which we call e-SNLI, can be used for various goals, such as obtaining full sentence justifications of a model’s decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets. Our dataset thus opens up a range of research directions for using natural language explanations, both for improving models and for asserting their trust.
Prototype-based Neural Network Layers: Incorporating Vector Quantization
Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretability. Prototype-based vector quantization methods on the other hand are known for being robust and interpretable. For this reason, we propose techniques and strategies to merge both approaches. This contribution will particularly highlight the similarities between them and outline how to construct a prototype-based classification layer for multilayer networks. Additionally, we provide an alternative, prototype-based, approach to the classical convolution operation. Numerical results are not part of this report, instead the focus lays on establishing a strong theoretical framework. By publishing our framework and the respective theoretical considerations and justifications before finalizing our numerical experiments we hope to jump-start the incorporation of prototype-based learning in neural networks and vice versa.
Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions
We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any additional sequential algorithm. The proposed method, Set Cross Entropy, has a natural information-theoretic interpretation and is related to the metrics defined for sets. We evaluate the proposed approach in two object reconstruction tasks and a rule learning task.
Learning Vine Copula Models For Synthetic Data Generation
A vine copula model is a flexible high-dimensional dependence model which uses only bivariate building blocks. However, the number of possible configurations of a vine copula grows exponentially as the number of variables increases, making model selection a major challenge in development. In this work, we formulate a vine structure learning problem with both vector and reinforcement learning representation. We use neural network to find the embeddings for the best possible vine model and generate a structure. Throughout experiments on synthetic and real-world datasets, we show that our proposed approach fits the data better in terms of log-likelihood. Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.
Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
A natural language interface (NLI) to structured query is intriguing due to its wide industrial applications and high economical values. In this work, we tackle the problem of domain adaptation for NLI with limited data on target domain. Two important approaches are considered: (a) effective general-knowledge-learning on source domain semantic parsing, and (b) data augmentation on target domain. We present a Structured Query Inference Network (SQIN) to enhance learning for domain adaptation, by separating schema information from NL and decoding SQL in a more structural-aware manner; we also propose a GAN-based augmentation technique (AugmentGAN) to mitigate the issue of lacking target domain data. We report solid results on GeoQuery, Overnight, and WikiSQL to demonstrate state-of-the-art performances for both in-domain and domain-transfer tasks.
Time is of the Essence: a Joint Hierarchical RNN and Point Process Model for Time and Item Predictions
In recent years session-based recommendation has emerged as an increasingly applicable type of recommendation. As sessions consist of sequences of events, this type of recommendation is a natural fit for Recurrent Neural Networks (RNNs). Several additions have been proposed for extending such models in order to handle specific problems or data. Two such extensions are 1.) modeling of inter-session relations for catching long term dependencies over user sessions, and 2.) modeling temporal aspects of user-item interactions. The former allows the session-based recommendation to utilize extended session history and inter-session information when providing new recommendations. The latter has been used to both provide state-of-the-art predictions for when the user will return to the service and also for improving recommendations. In this work we combine these two extensions in a joint model for the tasks of recommendation and return-time prediction. The model consists of a Hierarchical RNN for the inter-session and intra-session items recommendation extended with a Point Process model for the time-gaps between the sessions. The experimental results indicate that the proposed model improves recommendations significantly on two datasets over a strong baseline, while simultaneously improving return-time predictions over a baseline return-time prediction model.
Learning to Explain with Complemental Examples
This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples that render the decision interpretable. Focusing especially on the complementarity of the multimodal information, i.e., linguistic and visual examples, we attempt to achieve it by maximizing the interaction information, which provides a natural definition of complementarity from an information theoretical viewpoint. We propose a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector. Explanation models are trained collaboratively to maximize the interaction information to ensure the generated explanation are complemental to each other for the target. The results of experiments conducted on several datasets demonstrate the effectiveness of the proposed method.
Understanding Information Centrality Metric: A Simulation Approach
Identifying the central people in information flow networks is essential to understanding how people communicate and coordinate as well as who controls the information flows in the network. However, the appropriate usage of centrality metrics depends on an understanding of the type of network flow. Networks can vary in the way node-to-node transmission takes place, or in the way a course through the network is taken, thereby leading to different types of information flow processes. When metrics are used for an inappropriate flow process, the result of the metric can be misleading and often incorrect. In this paper we create a simulation of the flow of information in a network, and then we investigate the relation of information centrality as well as other network centralities, like betweenness, closeness and eigenvector along with the outcome of simulations with information flowing through walks rather than paths, trails or geodesics. We find that Information Centrality is more similar to Eigenvector and Degree centrality than to Closeness centrality as postulated by previous literature. We also find an interesting pattern emerge from the inter metric correlations.
JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the traditional requirement of quickly executing large computations, but also to support straightforward programming models for quickly implementing and experimenting with complex network structures. However, existing frameworks fail to excel in both departments simultaneously, leading to diverged efforts for optimizing performance and improving usability. This paper presents JANUS, a system that combines the advantages from both sides by transparently converting an imperative DL program written in Python, the de-facto scripting language for DL, into an efficiently executable symbolic dataflow graph. JANUS can convert various dynamic features of Python, including dynamic control flow, dynamic types, and impure functions, into elements of a symbolic dataflow graph. Experiments demonstrate that JANUS can achieve fast DL training by exploiting the techniques imposed by symbolic graph-based DL frameworks, while maintaining the simple and flexible programmability of imperative DL frameworks at the same time.
Self-Guided Belief Propagation — A Homotopy Continuation Method
We propose self-guided belief propagation (SBP) that modifies belief propagation (BP) by incorporating the pairwise potentials only gradually. This homotopy continuation method converges to a unique solution and increases the accuracy without increasing the computational burden. We apply SBP to grid graphs, complete graphs, and random graphs with random Ising potentials and show that: (i) SBP is superior in terms of accuracy whenever BP converges, and (ii) SBP obtains a unique, stable, and accurate solution whenever BP does not converge. We further provide a formal analysis to demonstrate that SBP obtains the global optimum of the Bethe approximation for attractive models with unidirectional fields.
Online scheduling of jobs with favorite machines
This work introduces a natural variant of the online machine scheduling problem on unrelated machines, which we refer to as the favorite machine model. In this model, each job has a minimum processing time on a certain set of machines, called favorite machines, and some longer processing times on other machines. This type of costs (processing times) arise quite naturally in many practical problems. In the online version, jobs arrive one by one and must be allocated irrevocably upon each arrival without knowing the future jobs. We consider online algorithms for allocating jobs in order to minimize the makespan. We obtain tight bounds on the competitive ratio of the greedy algorithm and characterize the optimal competitive ratio for the favorite machine model. Our bounds generalize the previous results of the greedy algorithm and the optimal algorithm for the unrelated machines and the identical machines. We also study a further restriction of the model, called the symmetric favorite machine model, where the machines are partitioned equally into two groups and each job has one of the groups as favorite machines. We obtain a 2.675-competitive algorithm for this case, and the best possible algorithm for the two machines case.
Realizing Edge Marketplaces: Challenges and Opportunities
The edge of the network has the potential to host services for supporting a variety of user applications, ranging in complexity from data preprocessing, image and video rendering, and interactive gaming, to embedded systems in autonomous cars and built environments. However, the computational and data resources over which such services are hosted, and the actors that interact with these services, have an intermittent availability and access profile, introducing significant risk for user applications that must rely on them. This article investigates the development of an edge marketplace, which is able to support multiple providers for offering services at the network edge, and to enable demand supply for influencing the operation of such a marketplace. Resilience, cost, and quality of service and experience will subsequently enable such a marketplace to adapt its services over time. This article also describes how distributed-ledger technologies (such as blockchains) provide a promising approach to support the operation of such a marketplace and regulate its behavior (such as the GDPR in Europe) and operation. Two application scenarios provide context for the discussion of how such a marketplace would function and be utilized in practice.
Regularized Fuzzy Neural Networks to Aid Effort Forecasting in the Construction and Software Development
Predicting the time to build software is a very complex task for software engineering managers. There are complex factors that can directly interfere with the productivity of the development team. Factors directly related to the complexity of the system to be developed drastically change the time necessary for the completion of the works with the software factories. This work proposes the use of a hybrid system based on artificial neural networks and fuzzy systems to assist in the construction of an expert system based on rules to support in the prediction of hours destined to the development of software according to the complexity of the elements present in the same. The set of fuzzy rules obtained by the system helps the management and control of software development by providing a base of interpretable estimates based on fuzzy rules. The model was submitted to tests on a real database, and its results were promissory in the construction of an aid mechanism in the predictability of the software construction.
Unstructured Semantic Model supported Deep Neural Network for Click-Through Rate Prediction
With the rapid development of online advertising and recommendation systems, click-through rate prediction is expected to play an increasingly important role.Recently many DNN-based models which follow a similar Embedding&MLP paradigm have been proposed, and have achieved good result in image/voice and nlp fields.In these methods the Wide&Deep model announced by Google plays a key role.Most models first map large scale sparse input features into low-dimensional vectors which are transformed to fixed-length vectors, then concatenated together before being fed into a multilayer perceptron (MLP) to learn non-linear relations among input features. The number of trainable variables normally grow dramatically the number of feature fields and the embedding dimension grow. It is a big challenge to get state-of-the-art result through training deep neural network and embedding together, which falls into local optimal or overfitting easily.In this paper, we propose an Unstructured Semantic Model (USM) to tackles this challenge by designing a orthogonal base convolution and pooling model which adaptively learn the multi-scale base semantic representation between features supervised by the click label.The output of USM are then used in the Wide&Deep for CTR prediction.Experiments on two public datasets as well as real Weibo production dataset with over 1 billion samples have demonstrated the effectiveness of our proposed approach with superior performance comparing to state-of-the-art methods.
On the sure screening property of the iterative sure independence screening algorithm
The iterative version of the sure independence screening algorithm (ISIS) has been widely employed in various scientific fields since Fan and Lv [2008] proposed it. Despite the outstanding performance of ISIS in extensive applications, its sure screening property has not been theoretically verified during the past decade. To fill this gap, we adapt a technique of Wang [2009] in the context of forward regression (FR) to prove the sure screening property of ISIS, without relying on the marginal correlation assumption.
A Deep Learning Framework for Semi-Supervised Cross-Modal Retrieval with Label Prediction
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant improvement over their unsupervised counterparts at the additional cost of labeling or annotation of the training data. Semi-supervised methods are recently becoming popular as they provide an elegant framework to balance the conflicting requirement of labeling cost and accuracy. In this work, we propose a novel deep semi-supervised framework which can seamlessly handle both labeled as well as unlabeled data. The network has two important components: (a) the label prediction component predicts the labels for the unlabeled portion of the data and then (b) a common modality-invariant representation is learned for cross-modal retrieval. The two parts of the network are trained sequentially one after the other. Extensive experiments on three standard benchmark datasets, Wiki, Pascal VOC and NUS-WIDE demonstrate that the proposed framework outperforms the state-of-the-art for both supervised and semi-supervised settings.
Deep Attention-guided Hashing
With the rapid growth of multimedia data (e.g., image, audio and video etc.) on the web, learning-based hashing techniques such as Deep Supervised Hashing (DSH) have proven to be very efficient for large-scale multimedia search. The recent successes seen in Learning-based hashing methods are largely due to the success of deep learning-based hashing methods. However, there are some limitations to previous learning-based hashing methods (e.g., the learned hash codes containing repetitive and highly correlated information). In this paper, we propose a novel learning-based hashing method, named Deep Attention-guided Hashing (DAgH). DAgH is implemented using two stream frameworks. The core idea is to use guided hash codes which are generated by the hashing network of the first stream framework (called first hashing network) to guide the training of the hashing network of the second stream framework (called second hashing network). Specifically, in the first network, it leverages an attention network and hashing network to generate the attention-guided hash codes from the original images. The loss function we propose contains two components: the semantic loss and the attention loss. The attention loss is used to punish the attention network to obtain the salient region from pairs of images; in the second network, these attention-guided hash codes are used to guide the training of the second hashing network (i.e., these codes are treated as supervised labels to train the second network). By doing this, DAgH can make full use of the most critical information contained in images to guide the second hashing network in order to learn efficient hash codes in a true end-to-end fashion. Results from our experiments demonstrate that DAgH can generate high quality hash codes and it outperforms current state-of-the-art methods on three benchmark datasets, CIFAR-10, NUS-WIDE, and ImageNet.
Compressive Classification (Machine Learning without learning)
Compressive learning is a framework where (so far unsupervised) learning tasks use not the entire dataset but a compressed summary (sketch) of it. We propose a compressive learning classification method, and a novel sketch function for images.
Necessary and Probably Sufficient Test for Finding Valid Instrumental Variables
Can instrumental variables be found from data? While instrumental variable (IV) methods are widely used to identify causal effect, testing their validity from observed data remains a challenge. This is because validity of an IV depends on two assumptions, exclusion and as-if-random, that are largely believed to be untestable from data. In this paper, we show that under certain conditions, testing for instrumental variables is possible. We build upon prior work on necessary tests to derive a test that characterizes the odds of being a valid instrument, thus yielding the name ‘necessary and probably sufficient’. The test works by defining the class of invalid-IV and valid-IV causal models as Bayesian generative models and comparing their marginal likelihood based on observed data. When all variables are discrete, we also provide a method to efficiently compute these marginal likelihoods. We evaluate the test on an extensive set of simulations for binary data, inspired by an open problem for IV testing proposed in past work. We find that the test is most powerful when an instrument follows monotonicity—effect on treatment is either non-decreasing or non-increasing—and has moderate-to-weak strength; incidentally, such instruments are commonly used in observational studies. Among as-if-random and exclusion, it detects exclusion violations with higher power. Applying the test to IVs from two seminal studies on instrumental variables and five recent studies from the American Economic Review shows that many of the instruments may be flawed, at least when all variables are discretized. The proposed test opens the possibility of data-driven validation and search for instrumental variables.
Matrix Factorization via Deep Learning
Matrix completion is one of the key problems in signal processing and machine learning. In recent years, deep-learning-based models have achieved state-of-the-art results in matrix completion. Nevertheless, they suffer from two drawbacks: (i) they can not be extended easily to rows or columns unseen during training; and (ii) their results are often degraded in case discrete predictions are required. This paper addresses these two drawbacks by presenting a deep matrix factorization model and a generic method to allow joint training of the factorization model and the discretization operator. Experiments on a real movie rating dataset show the efficacy of the proposed models.
Compositional Imitation Learning: Explaining and executing one task at a time
We introduce a framework for Compositional Imitation Learning and Execution (CompILE) of hierarchically-structured behavior. CompILE learns reusable, variable-length segments of behavior from demonstration data using a novel unsupervised, fully-differentiable sequence segmentation module. These learned behaviors can then be re-composed and executed to perform new tasks. At training time, CompILE auto-encodes observed behavior into a sequence of latent codes, each corresponding to a variable-length segment in the input sequence. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate our model in a challenging 2D multi-task environment and show that CompILE can find correct task boundaries and event encodings in an unsupervised manner without requiring annotated demonstration data. Latent codes and associated behavior policies discovered by CompILE can be used by a hierarchical agent, where the high-level policy selects actions in the latent code space, and the low-level, task-specific policies are simply the learned decoders. We found that our agent could learn given only sparse rewards, where agents without task-specific policies struggle.
Exploration versus exploitation in reinforcement learning: a stochastic control approach
We consider reinforcement learning (RL) in continuous time and study the problem of achieving the best trade-off between exploration of a black box environment and exploitation of current knowledge. We propose an entropy-regularized reward function involving the differential entropy of the distributions of actions, and motivate and devise an exploratory formulation for the feature dynamics that captures repetitive learning under exploration. The resulting optimization problem is a resurrection of the classical relaxed stochastic control. We carry out a complete analysis of the problem in the linear–quadratic (LQ) case and deduce that the optimal control distribution for balancing exploitation and exploration is Gaussian. This in turn interprets and justifies the widely adopted Gaussian exploration in RL, beyond its simplicity for sampling. Moreover, the exploitation and exploration are reflected respectively by the mean and variance of the Gaussian distribution. We also find that a more random environment contains more learning opportunities in the sense that less exploration is needed, other things being equal. As the weight of exploration decays to zero, we prove the convergence of the solution to the entropy-regularized LQ problem to that of the classical LQ problem. Finally, we characterize the cost of exploration, which is shown to be proportional to the entropy regularization weight and inversely proportional to the discount rate in the LQ case.
Modeling Theory of Mind for Autonomous Agents with Probabilistic Programs
As autonomous agents become more ubiquitous, they will eventually have to reason about the mental state of other agents, including those agents’ beliefs, desires and goals – so-called theory of mind reasoning. We introduce a collection of increasingly complex theory of mind models of a ‘chaser’ pursuing a ‘runner’, known as the Chaser-Runner model. We show that our implementation is a relatively straightforward theory of mind model that can capture a variety of rich behaviors, which in turn, increase runner detection rates relative to basic (non-theory-of-mind) models. In addition, our paper demonstrates that (1) using a planning-as-inference formulation based on nested importance sampling results in agents simultaneously reasoning about other agents’ plans and crafting counter-plans, (2) probabilistic programming is a natural way to describe models in which each uses complex primitives such as path planners to make decisions, and (3) allocating additional computation to perform nested reasoning about agents result in lower-variance estimates of expected utility.
• Capacity and outage analysis of a dual-hop decode-and-forward relay-aided NOMA scheme• Deep Generative Modeling of LiDAR Data• Parallel-tempered Stochastic Gradient Hamiltonian Monte Carlo for Approximate Multimodal Posterior Sampling• FRAME Revisited: An Interpretation View Based on Particle Evolution• Bag of Tricks for Image Classification with Convolutional Neural Networks• Reducing Seed Bias in Respondent-Driven Sampling by Estimating Block Transition Probabilities• A Retrieve-and-Edit Framework for Predicting Structured Outputs• Enhancing Physical Layer Security for NOMA Transmission in mmWave Drone Networks• Superion: Grammar-Aware Greybox Fuzzing• Adversarial Example Decomposition• Twitter-based traffic information system based on vector representations for words• PES: Priority Edge Sampling in Streaming Triangle Estimation• Federated Echo State Learning for Minimizing Breaks in Presence in Wireless Virtual Reality Networks• Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture• Distributed Communication-aware Motion Planning for Networked Mobile Robots under Formal Specifications• Stochastic Solution of Elliptic and Parabolic Boundary Value Problems for the Spectral Fractional Laplacian• Practical Text Classification With Large Pre-Trained Language Models• Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination• Parameter Re-Initialization through Cyclical Batch Size Schedules• Connectivity of single-element coextensions of a binary matroid• Time-Sequence Channel Inference for Beam Alignment in Vehicular Networks• Joint Ranging and Clock Synchronization for Dense Heterogeneous IoT Networks• Ladder Networks for Semi-Supervised Hyperspectral Image Classification• Inferring Remote Channel State Information: Cramér-Rao Lower Bound and Deep Learning Implementation• Solving multi-resource allocation and location problems in disaster management through linear programming• The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation• Classifying Collisions with Spatio-Temporal Action Graph Networks• Dynamic Sounding for Multi-User MIMO in Wireless LANs• A dual Simplex-type algorithm for the smallest enclosing ball of balls and related problems• Hypergraph matching for MU-MIMO user grouping in wireless LANs• Factorized Attention: Self-Attention with Linear Complexities• A Two-Step Learning and Interpolation Method for Location-Based Channel Database• Quantification and Analysis of Scientific Language Variation Across Research Fields• How fast can linear dynamical systems be learned?• Risk-averse Behavior Planning for Autonomous Driving under Uncertainty• Phase Retrieval by Alternating Minimization with Random Initialization• On $k$-Connected $Γ$-Extensions of Binary Matroids• Camera Based Optical Communications, Localization, Navigation, and Motion Capture: A Survey• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture• Conditional Video Generation Using Action-Appearance Captions• Multimodal Explanations by Predicting Counterfactuality in Videos• A Game-Theoretic Learning Framework for Multi-Agent Intelligent Wireless Networks• An Optimal Extraction Problem with Price Impact• Image Dehazing via Joint Estimation of Transmittance Map and Environmental Illumination• Digital Predistortion in Large-Array Digital Beamforming Transmitters• Implementation of Control Strategies for Sterile Insect Techniques• Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy• Characterization of forbidden subgraphs for bounded star chromatic number• Towards Continuous Domain adaptation for Healthcare• Rare Event Detection using Disentangled Representation Learning• FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis• Timeception for Complex Action Recognition• Polynomial integrals of magnetic geodesic flows on the 2-torus on several energy levels• Bispectral pairwise interacting source analysis for identifying systems of cross-frequency interacting brain sources from electroencephalographic or magnetoencephalographic signals• BSGD-TV: A parallel algorithm solving total variation constrained image reconstruction problems• Statistics with improper posteriors• Numerical assessment of the percolation threshold using complement networks• Generative Models for Fast Calorimeter Simulation.LHCb case• Local average treatment effects estimation via substantive model compatible multiple imputation• Using Binary File Format Description Languages for Documenting, Parsing, and Verifying Raw Data in TAIGA Experiment• Estimating cluster-level local average treatment effects in cluster randomised trials with non-adherence• From biological vision to unsupervised hierarchical sparse coding• Bridging trees for posterior inference on Ancestral Recombination Graphs• Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos• Megaphone: Live state migration for distributed streaming dataflows• Design and implementation of smart cooking based on amazon echo• The Lagrange approach in the monotone single index model• A new Bound for the Maker-Breaker Triangle Game• Design of an Efficient Single-Stage and 2-Stages Class-E Power Amplifier (2.4GHz) for Internet-of-Things• Estimating 6D Pose From Localizing Designated Surface Keypoints• Bad practices in evaluation methodology relevant to class-imbalanced problems• A multi-class structured dictionary learning method using discriminant atom selection• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection• Meta Learning Deep Visual Words for Fast Video Object Segmentation• Joint nonstationary blind source separation and spectral analysis• Column Generation Algorithms for Nonparametric Analysis of Random Utility Models• Inferring Point Clouds from Single Monocular Images by Depth Intermediation• Ballistic random walks in random environment as rough paths: convergence and area anomaly• Discrete-Time Distributed Observers over Jointly Connected Switching Networks and an Application• Untrodden pathways in the theory of the restricted partition function $p(n, N)$• Combinatorial persistency criteria for multicut and max-cut• Stability and moment bounds under utility-maximising service allocations, with applications to some infinite networks• Conflict-Free Colouring using Maximum Independent Set and Minimum Colouring• The Visual Centrifuge: Model-Free Layered Video Representations• Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks• Cross-spectral Periocular Recognition: A Survey• Performance of the smallest-variance-first rule in appointment sequencing• Centralized and Decentralized Cache-Aided Interference Management in Heterogeneous Parallel Channels• A Tight Upper Bound on Mutual Information• JOVIAL: Notebook-based Astronomical Data Analysis in the Cloud• On the stability of nucleic acid feedback controllers• An Inapproximability Result for the Target Set Selection Problem on Bipartite Graphs• Privacy-Preserving Distributed Deep Learning for Clinical Data• Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning• Natural Option Critic• Expanding search in the space of empirical ML• Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI• PolyMapper: Extracting City Maps using Polygons• A System for Efficient Communication between Patients and Pharmacies• Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain• Parallelising Particle Filters with Butterfly Interactions• Continuous User Authentication by Contactless Wireless Sensing• Content Authentication for Neural Imaging Pipelines: End-to-end Optimization of Photo Provenance in Complex Distribution Channels• Recovering Conductances of Resistor Networks in a Punctured Disk• SurfConv: Bridging 3D and 2D Convolution for RGBD Images• Phase transition encoded in neural network• A Face-to-Face Neural Conversation Model• Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models• LSCP: Locally Selective Combination in Parallel Outlier Ensembles• Control of automated guided vehicles without collision by quantum annealer and digital devices• Colouring triangle-free graphs with local list sizes• Information Percolation and Cutoff for the Random-Cluster Model• Fast Iterative Shrinkage for Signal Declipping and Dequantization• Towards generative adversarial networks as a new paradigm for radiology education• Particle identification in ground-based gamma-ray astronomy using convolutional neural networks• Batch Selection for Parallelisation of Bayesian Quadrature• A novel database of Children’s Spontaneous Facial Expressions (LIRIS-CSE)• Private Information Retrieval in Graph Based Replication Systems• Information Extraction Framework to Build Legislation Network• Multilevel MIMO Detection with Deep Learning• Optimal Sensor and Actuator Placement using Balanced Model Reduction• A Duality-Based Unified Approach to Bayesian Mechanism Design• On Turán problems for Cartesian products of graphs• Detect-to-Retrieve: Efficient Regional Aggregation for Image Search• Two-Step Many-Objective Optimal Power Flow Based on Knee Point-Driven Evolutionary Algorithm• A Parallel Double Greedy Algorithm for Submodular Maximization• Improving Semantic Segmentation via Video Propagation and Label Relaxation• Monocular Total Capture: Posing Face, Body, and Hands in the Wild• AutoFocus: Efficient Multi-Scale Inference• Learning 3D Human Dynamics from Video• Diameter Spanner, Eccentricity Spanner, and Approximating Extremal Graph Distances: Static, Dynamic, and Fault Tolerant
Like this:
Like Loading…
Related