Paper Group ANR 145
DESPOT: Online POMDP Planning with Regularization. Rough Set Based Color Channel Selection. A penalized likelihood method for classification with matrix-valued predictors. Are Face and Object Recognition Independent? A Neurocomputational Modeling Exploration. Collaborative prediction with expert advice. Quantifier Scope in Categorical Compositional …
DESPOT: Online POMDP Planning with Regularization
| Title | DESPOT: Online POMDP Planning with Regularization |
| Authors | Nan Ye, Adhiraj Somani, David Hsu, Wee Sun Lee |
| Abstract | The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the “curse of dimensionality” and the “curse of history”. To overcome these challenges, we introduce the Determinized Sparse Partially Observable Tree (DESPOT), a sparse approximation of the standard belief tree, for online planning under uncertainty. A DESPOT focuses online planning on a set of randomly sampled scenarios and compactly captures the “execution” of all policies under these scenarios. We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy. Leveraging this result, we give an anytime online planning algorithm, which searches a DESPOT for a policy that optimizes a regularized objective function. Regularization balances the estimated value of a policy under the sampled scenarios and the policy size, thus avoiding overfitting. The algorithm demonstrates strong experimental results, compared with some of the best online POMDP algorithms available. It has also been incorporated into an autonomous driving system for real-time vehicle control. The source code for the algorithm is available online. |
| Tasks | Autonomous Driving |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03250v3 |
| http://arxiv.org/pdf/1609.03250v3.pdf | |
| PWC | https://paperswithcode.com/paper/despot-online-pomdp-planning-with |
| Repo | |
| Framework | |
Rough Set Based Color Channel Selection
| Title | Rough Set Based Color Channel Selection |
| Authors | Soumyabrata Dev, Florian M. Savoy, Yee Hui Lee, Stefan Winkler |
| Abstract | Color channel selection is essential for accurate segmentation of sky and clouds in images obtained from ground-based sky cameras. Most prior works in cloud segmentation use threshold based methods on color channels selected in an ad-hoc manner. In this letter, we propose the use of rough sets for color channel selection in visible-light images. Our proposed approach assesses color channels with respect to their contribution for segmentation, and identifies the most effective ones. |
| Tasks | |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.00931v1 |
| http://arxiv.org/pdf/1611.00931v1.pdf | |
| PWC | https://paperswithcode.com/paper/rough-set-based-color-channel-selection |
| Repo | |
| Framework | |
A penalized likelihood method for classification with matrix-valued predictors
| Title | A penalized likelihood method for classification with matrix-valued predictors |
| Authors | Aaron J. Molstad, Adam J. Rothman |
| Abstract | We propose a penalized likelihood method to fit the linear discriminant analysis model when the predictor is matrix valued. We simultaneously estimate the means and the precision matrix, which we assume has a Kronecker product decomposition. Our penalties encourage pairs of response category mean matrices to have equal entries and also encourage zeros in the precision matrix. To compute our estimators, we use a blockwise coordinate descent algorithm. To update the optimization variables corresponding to response category mean matrices, we use an alternating minimization algorithm that takes advantage of the Kronecker structure of the precision matrix. We show that our method can outperform relevant competitors in classification, even when our modeling assumptions are violated. We analyze an EEG dataset to demonstrate our method’s interpretability and classification accuracy. |
| Tasks | EEG |
| Published | 2016-09-23 |
| URL | http://arxiv.org/abs/1609.07386v2 |
| http://arxiv.org/pdf/1609.07386v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-penalized-likelihood-method-for |
| Repo | |
| Framework | |
Are Face and Object Recognition Independent? A Neurocomputational Modeling Exploration
| Title | Are Face and Object Recognition Independent? A Neurocomputational Modeling Exploration |
| Authors | Panqu Wang, Isabel Gauthier, Garrison Cottrell |
| Abstract | Are face and object recognition abilities independent? Although it is commonly believed that they are, Gauthier et al.(2014) recently showed that these abilities become more correlated as experience with nonface categories increases. They argued that there is a single underlying visual ability, v, that is expressed in performance with both face and nonface categories as experience grows. Using the Cambridge Face Memory Test and the Vanderbilt Expertise Test, they showed that the shared variance between Cambridge Face Memory Test and Vanderbilt Expertise Test performance increases monotonically as experience increases. Here, we address why a shared resource across different visual domains does not lead to competition and to an inverse correlation in abilities? We explain this conundrum using our neurocomputational model of face and object processing (The Model, TM). Our results show that, as in the behavioral data, the correlation between subordinate level face and object recognition accuracy increases as experience grows. We suggest that different domains do not compete for resources because the relevant features are shared between faces and objects. The essential power of experience is to generate a “spreading transform” for faces that generalizes to objects that must be individuated. Interestingly, when the task of the network is basic level categorization, no increase in the correlation between domains is observed. Hence, our model predicts that it is the type of experience that matters and that the source of the correlation is in the fusiform face area, rather than in cortical areas that subserve basic level categorization. This result is consistent with our previous modeling elucidating why the FFA is recruited for novel domains of expertise (Tong et al., 2008). |
| Tasks | Object Recognition |
| Published | 2016-04-26 |
| URL | http://arxiv.org/abs/1604.07872v1 |
| http://arxiv.org/pdf/1604.07872v1.pdf | |
| PWC | https://paperswithcode.com/paper/are-face-and-object-recognition-independent-a |
| Repo | |
| Framework | |
Collaborative prediction with expert advice
| Title | Collaborative prediction with expert advice |
| Authors | Paul Christiano |
| Abstract | Many practical learning systems aggregate data across many users, while learning theory traditionally considers a single learner who trusts all of their observations. A case in point is the foundational learning problem of prediction with expert advice. To date, there has been no theoretical study of the general collaborative version of prediction with expert advice, in which many users face a similar problem and would like to share their experiences in order to learn faster. A key issue in this collaborative framework is robustness: generally algorithms that aggregate data are vulnerable to manipulation by even a small number of dishonest users. We exhibit the first robust collaborative algorithm for prediction with expert advice. When all users are honest and have similar tastes our algorithm matches the performance of pooling data and using a traditional algorithm. But our algorithm also guarantees that adding users never significantly degrades performance, even if the additional users behave adversarially. We achieve strong guarantees even when the overwhelming majority of users behave adversarially. As a special case, our algorithm is extremely robust to variation amongst the users. |
| Tasks | |
| Published | 2016-03-20 |
| URL | http://arxiv.org/abs/1603.06265v3 |
| http://arxiv.org/pdf/1603.06265v3.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-prediction-with-expert-advice |
| Repo | |
| Framework | |
Quantifier Scope in Categorical Compositional Distributional Semantics
| Title | Quantifier Scope in Categorical Compositional Distributional Semantics |
| Authors | Mehrnoosh Sadrzadeh |
| Abstract | In previous work with J. Hedges, we formalised a generalised quantifiers theory of natural language in categorical compositional distributional semantics with the help of bialgebras. In this paper, we show how quantifier scope ambiguity can be represented in that setting and how this representation can be generalised to branching quantifiers. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1608.01404v1 |
| http://arxiv.org/pdf/1608.01404v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantifier-scope-in-categorical-compositional |
| Repo | |
| Framework | |
A Set Theoretic Approach for Knowledge Representation: the Representation Part
| Title | A Set Theoretic Approach for Knowledge Representation: the Representation Part |
| Authors | Yi Zhou |
| Abstract | In this paper, we propose a set theoretic approach for knowledge representation. While the syntax of an application domain is captured by set theoretic constructs including individuals, concepts and operators, knowledge is formalized by equality assertions. We first present a primitive form that uses minimal assumed knowledge and constructs. Then, assuming naive set theory, we extend it by definitions, which are special kinds of knowledge. Interestingly, we show that the primitive form is expressive enough to define logic operators, not only propositional connectives but also quantifiers. |
| Tasks | |
| Published | 2016-03-11 |
| URL | http://arxiv.org/abs/1603.03511v1 |
| http://arxiv.org/pdf/1603.03511v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-set-theoretic-approach-for-knowledge |
| Repo | |
| Framework | |
Towards Machine Intelligence
| Title | Towards Machine Intelligence |
| Authors | Kamil Rocki |
| Abstract | There exists a theory of a single general-purpose learning algorithm which could explain the principles of its operation. This theory assumes that the brain has some initial rough architecture, a small library of simple innate circuits which are prewired at birth and proposes that all significant mental algorithms can be learned. Given current understanding and observations, this paper reviews and lists the ingredients of such an algorithm from both architectural and functional perspectives. |
| Tasks | |
| Published | 2016-03-27 |
| URL | http://arxiv.org/abs/1603.08262v1 |
| http://arxiv.org/pdf/1603.08262v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-machine-intelligence |
| Repo | |
| Framework | |
Point Pair Feature based Object Detection for Random Bin Picking
| Title | Point Pair Feature based Object Detection for Random Bin Picking |
| Authors | Wim Abbeloos, Toon Goedemé |
| Abstract | Point pair features are a popular representation for free form 3D object detection and pose estimation. In this paper, their performance in an industrial random bin picking context is investigated. A new method to generate representative synthetic datasets is proposed. This allows to investigate the influence of a high degree of clutter and the presence of self similar features, which are typical to our application. We provide an overview of solutions proposed in literature and discuss their strengths and weaknesses. A simple heuristic method to drastically reduce the computational complexity is introduced, which results in improved robustness, speed and accuracy compared to the naive approach. |
| Tasks | 3D Object Detection, Object Detection, Pose Estimation |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01288v1 |
| http://arxiv.org/pdf/1612.01288v1.pdf | |
| PWC | https://paperswithcode.com/paper/point-pair-feature-based-object-detection-for |
| Repo | |
| Framework | |
Hashmod: A Hashing Method for Scalable 3D Object Detection
| Title | Hashmod: A Hashing Method for Scalable 3D Object Detection |
| Authors | Wadim Kehl, Federico Tombari, Nassir Navab, Slobodan Ilic, Vincent Lepetit |
| Abstract | We present a scalable method for detecting objects and estimating their 3D poses in RGB-D data. To this end, we rely on an efficient representation of object views and employ hashing techniques to match these views against the input frame in a scalable way. While a similar approach already exists for 2D detection, we show how to extend it to estimate the 3D pose of the detected objects. In particular, we explore different hashing strategies and identify the one which is more suitable to our problem. We show empirically that the complexity of our method is sublinear with the number of objects and we enable detection and pose estimation of many 3D objects with high accuracy while outperforming the state-of-the-art in terms of runtime. |
| Tasks | 3D Object Detection, Object Detection, Pose Estimation |
| Published | 2016-07-20 |
| URL | http://arxiv.org/abs/1607.06062v1 |
| http://arxiv.org/pdf/1607.06062v1.pdf | |
| PWC | https://paperswithcode.com/paper/hashmod-a-hashing-method-for-scalable-3d |
| Repo | |
| Framework | |
Spatial Relationship Based Features for Indian Sign Language Recognition
| Title | Spatial Relationship Based Features for Indian Sign Language Recognition |
| Authors | B. M. Chethana Kumara, H. S. Nagendraswamy, R. Lekha Chinmayi |
| Abstract | In this paper, the task of recognizing signs made by hearing impaired people at sentence level has been addressed. A novel method of extracting spatial features to capture hand movements of a signer has been proposed. Frames of a given video of a sign are preprocessed to extract face and hand components of a signer. The local centroids of the extracted components along with the global centroid are exploited to extract spatial features. The concept of interval valued type symbolic data has been explored to capture variations in the same sign made by the different signers at different instances of time. A suitable symbolic similarity measure is studied to establish matching between test and reference signs and a simple nearest neighbour classifier is used to recognize an unknown sign as one among the known signs by specifying a desired level of threshold. An extensive experimentation is conducted on a considerably large database of signs created by us during the course of research work in order to evaluate the performance of the proposed system |
| Tasks | Sign Language Recognition |
| Published | 2016-10-09 |
| URL | http://arxiv.org/abs/1610.07995v1 |
| http://arxiv.org/pdf/1610.07995v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-relationship-based-features-for |
| Repo | |
| Framework | |
Multi-modal dictionary learning for image separation with application in art investigation
| Title | Multi-modal dictionary learning for image separation with application in art investigation |
| Authors | Nikos Deligiannis, Joao F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies |
| Abstract | In support of art investigation, we propose a new source separation method that unmixes a single X-ray scan acquired from double-sided paintings. In this problem, the X-ray signals to be separated have similar morphological characteristics, which brings previous source separation methods to their limits. Our solution is to use photographs taken from the front and back-side of the panel to drive the separation process. The crux of our approach relies on the coupling of the two imaging modalities (photographs and X-rays) using a novel coupled dictionary learning framework able to capture both common and disparate features across the modalities using parsimonious representations; the common component models features shared by the multi-modal images, whereas the innovation component captures modality-specific information. As such, our model enables the formulation of appropriately regularized convex optimization procedures that lead to the accurate separation of the X-rays. Our dictionary learning framework can be tailored both to a single- and a multi-scale framework, with the latter leading to a significant performance improvement. Moreover, to improve further on the visual quality of the separated images, we propose to train coupled dictionaries that ignore certain parts of the painting corresponding to craquelure. Experimentation on synthetic and real data - taken from digital acquisition of the Ghent Altarpiece (1432) - confirms the superiority of our method against the state-of-the-art morphological component analysis technique that uses either fixed or trained dictionaries to perform image separation. |
| Tasks | Dictionary Learning |
| Published | 2016-07-14 |
| URL | http://arxiv.org/abs/1607.04147v1 |
| http://arxiv.org/pdf/1607.04147v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-dictionary-learning-for-image |
| Repo | |
| Framework | |
An Improved Gap-Dependency Analysis of the Noisy Power Method
| Title | An Improved Gap-Dependency Analysis of the Noisy Power Method |
| Authors | Maria Florina Balcan, Simon S. Du, Yining Wang, Adams Wei Yu |
| Abstract | We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over the “consecutive” spectral gap $(\sigma_k-\sigma_{k+1})$ of an input data matrix, which could be very small and hence limits the algorithm’s applicability. In this paper, we present a new analysis of the noisy power method that achieves improved gap dependency for both sample complexity and noise tolerance bounds. More specifically, we improve the dependency over $(\sigma_k-\sigma_{k+1})$ to dependency over $(\sigma_k-\sigma_{q+1})$, where $q$ is an intermediate algorithm parameter and could be much larger than the target rank $k$. Our proofs are built upon a novel characterization of proximity between two subspaces that differ from canonical angle characterizations analyzed in previous works. Finally, we apply our improved bounds to distributed private PCA and memory-efficient streaming PCA and obtain bounds that are superior to existing results in the literature. |
| Tasks | |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07046v1 |
| http://arxiv.org/pdf/1602.07046v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-improved-gap-dependency-analysis-of-the |
| Repo | |
| Framework | |
Predicting the consequence of action in digital control state spaces
| Title | Predicting the consequence of action in digital control state spaces |
| Authors | Emmanuel Daucé |
| Abstract | The objective of this dissertation is to shed light on some fundamental impediments in learning control laws in continuous state spaces. In particular, if one wants to build artificial devices capable to learn motor tasks the same way they learn to classify signals and images, one needs to establish control rules that do not necessitate comparisons between quantities of the surrounding space. We propose, in that context, to take inspiration from the “end effector control” principle, as suggested by neuroscience studies, as opposed to the “displacement control” principle used in the classical control theory. |
| Tasks | |
| Published | 2016-09-30 |
| URL | http://arxiv.org/abs/1609.09681v1 |
| http://arxiv.org/pdf/1609.09681v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-consequence-of-action-in |
| Repo | |
| Framework | |
Approximate Joint Matrix Triangularization
| Title | Approximate Joint Matrix Triangularization |
| Authors | Nicolo Colombo, Nikos Vlassis |
| Abstract | We consider the problem of approximate joint triangularization of a set of noisy jointly diagonalizable real matrices. Approximate joint triangularizers are commonly used in the estimation of the joint eigenstructure of a set of matrices, with applications in signal processing, linear algebra, and tensor decomposition. By assuming the input matrices to be perturbations of noise-free, simultaneously diagonalizable ground-truth matrices, the approximate joint triangularizers are expected to be perturbations of the exact joint triangularizers of the ground-truth matrices. We provide a priori and a posteriori perturbation bounds on the `distance’ between an approximate joint triangularizer and its exact counterpart. The a priori bounds are theoretical inequalities that involve functions of the ground-truth matrices and noise matrices, whereas the a posteriori bounds are given in terms of observable quantities that can be computed from the input matrices. From a practical perspective, the problem of finding the best approximate joint triangularizer of a set of noisy matrices amounts to solving a nonconvex optimization problem. We show that, under a condition on the noise level of the input matrices, it is possible to find a good initial triangularizer such that the solution obtained by any local descent-type algorithm has certain global guarantees. Finally, we discuss the application of approximate joint matrix triangularization to canonical tensor decomposition and we derive novel estimation error bounds. | |
| Tasks | |
| Published | 2016-07-02 |
| URL | http://arxiv.org/abs/1607.00514v1 |
| http://arxiv.org/pdf/1607.00514v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-joint-matrix-triangularization |
| Repo | |
| Framework | |
