Latest in cs.lg
total 42836took 0.12s
ColorNet -- Estimating Colorfulness in Natural ImagesAug 22 2019Measuring the colorfulness of a natural or virtual scene is critical for many applications in image processing field ranging from capturing to display. In this paper, we propose the first deep learning-based colorfulness estimation metric. For this purpose, ... More The many Shapley values for model explanationAug 22 2019The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The Shapley value [1] is known to be the unique method that satisfies certain desirable properties, and this motivates ... More Noise Flow: Noise Modeling with Conditional Normalizing FlowsAug 22 2019Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a coarse approximation ... More Efficient Cross-Validation of Echo State NetworksAug 22 2019Echo State Networks (ESNs) are known for their fast and precise one-shot learning of time series. But they often need good hyper-parameter tuning for best performance. For this good validation is key, but usually, a single validation split is used. In ... More Practical Risk Measures in Reinforcement LearningAug 22 2019Practical application of Reinforcement Learning (RL) often involves risk considerations. We study a generalized approximation scheme for risk measures, based on Monte-Carlo simulations, where the risk measures need not necessarily be \emph{coherent}. ... More LoRAS: An oversampling approach for imbalanced datasetsAug 22 2019The Synthetic Minority Oversampling TEchnique (SMOTE) is widely-used for the analysis of imbalanced datasets.It is known that SMOTE frequently over-generalizes the minority class, leading to misclassifications for the majority class, and effecting the ... More Text Summarization with Pretrained EncodersAug 22 2019Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how BERT can be usefully ... More Measuring the Business Value of Recommender SystemsAug 22 2019Recommender Systems are nowadays successfully used by all major web sites (from e-commerce to social media) to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., ... More LEAP nets for power grid perturbationsAug 22 2019We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architeture LEAP net, ... More Semi-supervised Adversarial Active Learning on Attributed GraphsAug 22 2019Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional independent and identically distributed ... More A Neural Network for Semi-Supervised Learning on ManifoldsAug 21 2019Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose a feed-forward ... More BRIDGE: Byzantine-resilient Decentralized Gradient DescentAug 21 2019Decentralized optimization techniques are increasingly being used to learn machine learning models from data distributed over multiple locations without gathering the data at any one location. Unfortunately, methods that are designed for faultless networks ... More Boundary Aware Networks for Medical Image SegmentationAug 21 2019Fully convolutional neural networks (CNNs) have proven to be effective at representing and classifying textural information, thus transforming image intensity into output class masks that achieve semantic image segmentation. In medical image analysis, ... More Coarse-to-fine Optimization for Speech EnhancementAug 21 2019In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the enhanced speech ... More Testing Robustness Against Unforeseen AdversariesAug 21 2019Considerable work on adversarial defense has studied robustness to a fixed, known family of adversarial distortions, most frequently L_p-bounded distortions. In reality, the specific form of attack will rarely be known and adversaries are free to employ ... More QCNN: Quantile Convolutional Neural NetworkAug 21 2019A dilated causal one-dimensional convolutional neural network architecture is proposed for quantile regression. The model can forecast any arbitrary quantile, and it can be trained jointly on multiple similar time series. An application to Value at Risk ... More Estimation of perceptual scales using ordinal embeddingAug 21 2019In this paper, we address the problem of measuring and analysing sensation, the subjective magnitude of one's experience. We do this in the context of the method of triads: the sensation of the stimulus is evaluated via relative judgments of the form: ... More Design Space of Behaviour Planning for Autonomous DrivingAug 21 2019We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. To aid the design process, in this work we decompose the design ... More Federated Learning: Challenges, Methods, and Future DirectionsAug 21 2019Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges ... More A CNN toolbox for skin cancer classificationAug 21 2019We describe a software toolbox for the configuration of deep neural networks in the domain of skin cancer classification. The implemented software architecture allows developers to quickly set up new convolutional neural network (CNN) architectures and ... More Minimum Description Length RevisitedAug 21 2019This is an up-to-date introduction to and overview of the Minimum Description Length (MDL) Principle, a theory of inductive inference that can be applied to general problems in statistics, machine learning and pattern recognition. While MDL was originally ... More U-Net Training with Instance-Layer NormalizationAug 21 2019Normalization layers are essential in a Deep Convolutional Neural Network (DCNN). Various normalization methods have been proposed. The statistics used to normalize the feature maps can be computed at batch, channel, or instance level. However, in most ... More Dialog State Tracking with Reinforced Data AugmentationAug 21 2019Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can ... More Decentralized Federated Learning: A Segmented Gossip ApproachAug 21 2019The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data. Conventional federated learning architecture, inherited ... More Restricted Recurrent Neural NetworksAug 21 2019Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including natural language ... More Hebbian Graph EmbeddingsAug 21 2019Representation learning has recently been successfully used to create vector representations of entities in language learning, recommender systems and in similarity learning. Graph embeddings exploit the locality structure of a graph and generate embeddings ... More Asymmetric Non-local Neural Networks for Semantic SegmentationAug 21 2019The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, ... More Asymmetric Non-local Neural Networks for Semantic SegmentationAug 21 2019Aug 22 2019The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, ... More Deep Reinforcement Learning for Foreign Exchange TradingAug 21 2019Reinforcement learning can interact with the environment and is suitable for applications in decision control systems. Therefore, we used the reinforcement learning method to establish a foreign exchange transaction, avoiding the long-standing problem ... More AdaCliP: Adaptive Clipping for Private SGDAug 20 2019Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models ... More Detecting Gas Vapor Leaks Using Uncalibrated SensorsAug 20 2019Chemical and infra-red sensors generate distinct responses under similar conditions because of sensor drift, noise or resolution errors. In this work, we use different time-series data sets obtained by infra-red and E-nose sensors in order to detect Volatile ... More Reinforcement Learning is not a Causal problemAug 20 2019We use an analogy between non-isomorphic mathematical structures defined over the same set and the algebras induced by associative and causal levels of information in order to argue that Reinforcement Learning, in its current formulation, is not a causal ... More Learning document embeddings along with their uncertaintiesAug 20 2019Majority of the text modelling techniques yield only point estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian ... More Developing Creative AI to Generate Sculptural ObjectsAug 20 2019We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical details of automatic art generation and the interaction between AI and people, ... More Phrase Localization Without Paired Training ExamplesAug 20 2019Localizing phrases in images is an important part of image understanding and can be useful in many applications that require mappings between textual and visual information. Existing work attempts to learn these mappings from examples of phrase-image ... More Data Management for Causal Algorithmic FairnessAug 20 2019Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we ... More Hotel Recommendation SystemAug 20 2019One of the first things to do while planning a trip is to book a good place to stay. Booking a hotel online can be an overwhelming task with thousands of hotels to choose from, for every destination. Motivated by the importance of these situations, we ... More Hotel Recommendation SystemAug 20 2019Aug 21 2019One of the first things to do while planning a trip is to book a good place to stay. Booking a hotel online can be an overwhelming task with thousands of hotels to choose from, for every destination. Motivated by the importance of these situations, we ... More