We study distributional similarity measures for the purpose of improvingprobability estimation for unseen cooccurrences. Our contributions arethree-fold: an empirical comparison of a broad range of measures; aclassification of similarity functions based on the information that theyincorporate; and the introduction of a novel function that is superior atevaluating potential proxy distributions.
translated by 谷歌翻译
Low-rank matrix approximation methods provide one of the simplest and most effective approaches to collaborative filtering. Such models are usually fitted to data by finding a MAP estimate of the model parameters, a procedure that can be performed efficiently even on very large datasets. However, unless the regularization parameters are tuned carefully, this approach is prone to overfit-ting because it finds a single point estimate of the parameters. In this paper we present a fully Bayesian treatment of the Probabilistic Matrix Factorization (PMF) model in which model capacity is controlled automatically by integrating over all model parameters and hyperparameters. We show that Bayesian PMF models can be efficiently trained using Markov chain Monte Carlo methods by applying them to the Netflix dataset, which consists of over 100 million movie ratings. The resulting models achieve significantly higher prediction accuracy than PMF models trained using MAP estimation.
translated by 谷歌翻译
Grounded cognition
分类:
Grounded cognition rejects traditional views that cognition is computation on amodal symbols in a modular system, independent of the brain's modal systems for perception, action, and introspec-tion. Instead, grounded cognition proposes that modal simulations, bodily states, and situated action underlie cognition. Accumulating behavioral and neural evidence supporting this view is reviewed from research on perception, memory, knowledge, language, thought, social cognition, and development. Theories of grounded cognition are also reviewed, as are origins of the area and common misperceptions of it. Theoretical, empirical, and methodological issues are raised whose future treatment is likely to affect the growth and impact of grounded cognition.
translated by 谷歌翻译
Tyrosine kinases of the Src-family are large allosteric enzymes that play a key role in cellular signaling. Conversion of the kinase from an inactive to an active state is accompanied by substantial structural changes. Here, we construct a coarse-grained model of the catalytic domain incorporating experimental structures for the two stable states, and simulate the dynamics of conformational transitions in kinase activation. We explore the transition energy landscapes by constructing a structural network among clusters of conformations from the simulations. From the structural network, two major ensembles of pathways for the activation are identified. In the first transition pathway, we find a coordinated switching mechanism of interactions among the aC helix, the activation-loop, and the b strands in the N-lobe of the catalytic domain. In a second pathway, the conformational change is coupled to a partial unfolding of the N-lobe region of the catalytic domain. We also characterize the switching mechanism for the aC helix and the activation-loop in detail. Finally, we test the performance of a Markov model and its ability to account for the structural kinetics in the context of Src conformational changes. Taken together, these results provide a broad framework for understanding the main features of the conformational transition taking place upon Src activation.
translated by 谷歌翻译
This paper presents an online learning algorithm for appearance based gaze estimation that allows free head movement in a casual desktop environment. Our method avoids the lengthy calibration stage using an incremental learning approach. Our system keeps running as a background process on the desktop PC and continuously updates the estimation parameters by taking user's operations on the PC monitor as input. To handle free head movement of a user, we propose a pose-based clustering approach that efficiently extends an appearance manifold model to handle the large variations of the head pose. The effectiveness of the proposed method is validated by quantitative performance evaluation with three users.
translated by 谷歌翻译
In this paper, we describe a novel, computationally efficient algorithm that facilitates the autonomous acquisition of readings from sensor networks (deciding when and which sensor to acquire readings from at any time), and which can, with minimal domain knowledge, perform a range of information processing tasks including modelling the accuracy of the sensor readings, predicting the value of missing sensor readings, and predicting how the monitored environmental variables will evolve into the future. Our motivating scenario is the need to provide situational awareness support to first responders at the scene of a large scale incident, and to this end, we describe a novel iterative formulation of a multi-output Gaussian process that can build and exploit a probabilistic model of the environmental variables being measured (including the correlations and delays that exist between them). We validate our approach using data collected from a network of weather sensors located on the south coast of England.
translated by 谷歌翻译
Many complex control problems require sophisticated solutions that are not amenable to traditional controller design. Not only is it difficult to model real world systems, but often it is unclear what kind of behavior is required to solve the task. Reinforcement learning (RL) approaches have made progress by using direct interaction with the task environment, but have so far not scaled well to large state spaces and environments that are not fully observable. In recent years, neuroevolution, the artificial evolution of neural networks, has had remarkable success in tasks that exhibit these two properties. In this paper, we compare a neuroevolution method called Cooperative Synapse Neuroevolution (CoSyNE), that uses cooperative coevolution at the level of individual synaptic weights, to a broad range of reinforcement learning algorithms on very difficult versions of the pole balancing problem that involve large (continuous) state spaces and hidden state. CoSyNE is shown to be significantly more efficient and powerful than the other methods on these tasks.
translated by 谷歌翻译
Finding good representations of text documents is crucial in information retrieval and classification systems. Today the most popular document representation is based on a vector of word counts in the document. This representation neither captures dependencies between related words, nor handles synonyms or polysemous words. In this paper, we propose an algorithm to learn text document representations based on semi-supervised au-toencoders that are stacked to form a deep network. The model can be trained efficiently on partially labeled corpora, producing very compact representations of documents, while retaining as much class information and joint word statistics as possible. We show that it is advantageous to exploit even a few labeled samples during training.
translated by 谷歌翻译
This paper introduces a novel design of an artificial neural network tailored for wafer-scale integration. The presented VLSI implementation includes continuous-time ana-log neurons with up to 16k inputs. A novel interconnection and routing scheme allows the mapping of a multitude of network models derived from biology on the VLSI neural network while maintaining a high resource usage. A single 20 cm wafer contains about 60 million synapses. The implemented neurons are highly accelerated compared to biological real time. The power consumption of the dense interconnection network providing the necessary communication bandwidth is a critical aspect of the system integration. A novel asynchronous low-voltage signaling scheme is presented that makes the wafer-scale approach feasible by limiting the total power consumption while simultaneously providing a flexible, programmable network topology.
translated by 谷歌翻译
This article presents a novel scale-and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (specifically, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper encompasses a detailed description of the detector and descriptor and then explores the effects of the most important parameters. We conclude the article with SURF's application to two challenging, yet converse goals: camera calibration as a special case of image registration, and object recognition. Our experiments underline SURF's usefulness in a broad range of topics in computer vision.
translated by 谷歌翻译
translated by 谷歌翻译
We consider the problem of learning accurate models from multiple sources of "nearby" data. Given distinct samples from multiple data sources and estimates of the dissimilarities between these sources, we provide a general theory of which samples should be used to learn models for each source. This theory is applicable in a broad decision-theoretic learning framework, and yields general results for classification and regression. A key component of our approach is the development of approximate triangle inequalities for expected loss, which may be of independent interest. We discuss the related problem of learning parameters of a distribution from multiple data sources. Finally, we illustrate our theory through a series of synthetic simulations.
translated by 谷歌翻译
In this paper, we present a study of a novel summarization problem, i.e., summarizing the impact of a scientific publication. Given a paper and its citation context, we study how to extract sentences that can represent the most influential content of the paper. We propose language modeling methods for solving this problem, and study how to incorporate features such as authority and proximity to accurately estimate the impact language model. Experiment results on a SIGIR publication collection show that the proposed methods are effective for generating impact-based summaries .
translated by 谷歌翻译
In problems where input features have varying amounts of noise, using distinct regularization hyperparameters for different features provides an effective means of managing model complexity. While regularizers for neural networks and support vector machines often rely on multiple hyperparameters, regularizers for structured prediction models (used in tasks such as sequence labeling or parsing) typically rely only on a single shared hyperparameter for all features. In this paper, we consider the problem of choosing regularization hyperparameters for log-linear models, a class of structured prediction probabilistic models which includes conditional random fields (CRFs). Using an implicit differentiation trick, we derive an efficient gradient-based method for learning Gaussian regularization priors with multiple hyperparameters. In both simulations and the real-world task of computational RNA secondary structure prediction, we find that multiple hy-perparameter learning can provide a significant boost in accuracy compared to using only a single regularization hyperparameter.
translated by 谷歌翻译
The variation caused by aging has not received adequate attention compared with pose, lighting, and expression variations. Aging is a complex process that affects both the 3D shape of the face and its texture (e.g., wrinkles). While the facial age modeling has been widely studied in computer graphics community, only a few studies have been reported in computer vision literature on age-invariant face recognition. We propose an automatic aging simulation technique that can assist any existing face recognition engine for aging-invariant face recognition. We learn the aging patterns of shape and the corresponding texture in 3D domain by adapting a 3D morphable model to the 2D aging database (public domain FG-NET). At recognition time, each probe and all gallery images are modified to compensate for the age-induced variation using an intermediate 3D model deformation and a texture modification, prior to matching. The proposed approach is evaluated on a set of age-separated probe and gallery data using a state-of-the-art commercial face recognition engine, FaceVACS. Use of 3D aging model improves the rank-1 matching accuracy on FG-NET database from 28.0% to 37.8%, on average.
translated by 谷歌翻译
We consider an autoregressive moving-average (ARMA) time series where the observations are perturbed by two kinds of outliers: an additive outlier (AO) or an innovation outlier (IO). Abraham and Yatawara [Journal of Time Series Analysis (1988) Vol. 9, pp. 109-19] investigate a sequential test which successively detects and identifies the outlier type. In this article, we propose an extension of this test, called Ômodified sequential testÕ, which performs the two procedures simultaneously and coherently. The asymptotic distribution of the test statistic is calculated under the null hypothesis that no outlier is present. Comparison of the two test procedures using simulation experiments shows that the proposed test gives a better power especially in the case of an IO.
translated by 谷歌翻译
Online services such as web search, news portals, and e-commerce applications face the challenge of providing high-quality experiences to a large, heterogeneous user base. Recent efforts have highlighted the potential to improve performance by personalizing services based on special knowledge about users. For example, a user's location, demographics, and search and browsing history may be useful in enhancing the results offered in response to web search queries. However, reasonable concerns about privacy by both users, providers, and government agencies acting on behalf of citizens , may limit access to such information. We introduce and explore an economics of privacy in personalization, where people can opt to share personal information in return for enhancements in the quality of an online service. We focus on the example of web search and formulate realistic objective functions for search efficacy and privacy. We demonstrate how we can identify a near-optimal solution to the utility-privacy tradeoff. We evaluate the methodology on data drawn from a log of the search activity of volunteer participants. We separately assess users' preferences about privacy and utility via a large-scale survey, aimed at eliciting preferences about peoples' willingness to trade the sharing of personal data in returns for gains in search efficiency. We show that a significant level of personalization can be achieved using only a small amount of information about users.
translated by 谷歌翻译
Scan and segmented scan algorithms are crucial building blocks for a great many data-parallel algorithms. Segmented scan and related primitives also provide the necessary support for the flattening transform, which allows for nested data-parallel programs to be compiled into flat data-parallel languages. In this paper, we describe the design of efficient scan and segmented scan parallel prim-itives in CUDA for execution on GPUs. Our algorithms are designed using a divide-and-conquer approach that builds all scan primitives on top of a set of primitive intra-warp scan routines. We demonstrate that this design methodology results in routines that are simple, highly efficient, and free of irregular access patterns that lead to memory bank conflicts. These algorithms form the basis for current and upcoming releases of the widely used CUDPP library.
translated by 谷歌翻译
Stage is a C++ software library that simulates multiple mobile robots. Stage version 2, as the simulation backend for the Player/Stage system, may be the most commonly used robot simulator in research and university teaching today. Development of Stage version 3 has focused on improving scalability, usability, and portability. This paper examines Stage's scalability. We propose a simple benchmark for multi-robot simulator performance, and present results for Stage. Run time is shown to scale approximately linearly with population size up to 100,000 robots. For example, Stage simulates 1 simple robot at around 1,000 times faster than real time, and 1,000 simple robots at around real time. These results suggest that Stage may be useful for swarm robotics researchers who would otherwise use custom simulators, with their attendant disadvantages in terms of code reuse and transparency.
translated by 谷歌翻译