Paper Group ANR 802
Exploring Neural Methods for Parsing Discourse Representation Structures. Fixation properties of multiple cooperator configurations on regular graphs. Optimal Neural Network Feature Selection for Spatial-Temporal Forecasting. Syllabification by Phone Categorization. 3D Shape Perception from Monocular Vision, Touch, and Shape Priors. Analysing Symbo …
Exploring Neural Methods for Parsing Discourse Representation Structures
Title | Exploring Neural Methods for Parsing Discourse Representation Structures |
Authors | Rik van Noord, Lasha Abzianidze, Antonio Toral, Johan Bos |
Abstract | Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn-indices increases parser performance. Adding silver training data boosts performance even further. |
Tasks | Semantic Parsing |
Published | 2018-10-30 |
URL | http://arxiv.org/abs/1810.12579v1 |
http://arxiv.org/pdf/1810.12579v1.pdf | |
PWC | https://paperswithcode.com/paper/exploring-neural-methods-for-parsing |
Repo | |
Framework | |
Fixation properties of multiple cooperator configurations on regular graphs
Title | Fixation properties of multiple cooperator configurations on regular graphs |
Authors | Hendrik Richter |
Abstract | Whether or not cooperation is favored in evolutionary games on graphs depends on the population structure and spatial properties of the interaction network. Population structures can be expressed as configurations. Such configurations extend scenarios with a single cooperator among defectors to any number of cooperators and any arrangement of cooperators and defectors. Thus, as a single cooperator can be interpreted as a lone mutant, the discussion about fixation properties based on configurations also applies to multiple mutants. For interaction networks modeled as regular graphs and for weak selection, the emergence of cooperation can be assessed by structure coefficients, which are specific for a configuration and a graph. We analyze these structure coefficients and particularly show that under certain conditions the coefficients strongly correlate to the average shortest path length between cooperators on the evolutionary graph. Thus,for multiple cooperators fixation properties on regular evolutionary graphs can be linked to cooperator path length. |
Tasks | |
Published | 2018-11-16 |
URL | http://arxiv.org/abs/1811.06809v2 |
http://arxiv.org/pdf/1811.06809v2.pdf | |
PWC | https://paperswithcode.com/paper/fixation-properties-of-multiple-cooperator |
Repo | |
Framework | |
Optimal Neural Network Feature Selection for Spatial-Temporal Forecasting
Title | Optimal Neural Network Feature Selection for Spatial-Temporal Forecasting |
Authors | Eurico Covas, Emmanouil Benetos |
Abstract | In this paper, we show empirical evidence on how to construct the optimal feature selection or input representation used by the input layer of a feedforward neural network for the propose of forecasting spatial-temporal signals. The approach is based on results from dynamical systems theory, namely the non-linear embedding theorems. We demonstrate it for a variety of spatial-temporal signals, with one spatial and one temporal dimensions, and show that the optimal input layer representation consists of a grid, with spatial/temporal lags determined by the minimum of the mutual information of the spatial/temporal signals and the number of points taken in space/time decided by the embedding dimension of the signal. We present evidence of this proposal by running a Monte Carlo simulation of several combinations of input layer feature designs and show that the one predicted by the non-linear embedding theorems seems to be optimal or close of optimal. In total we show evidence in four unrelated systems: a series of coupled Henon maps; a series of couple Ordinary Differential Equations (Lorenz-96) phenomenologically modelling atmospheric dynamics; the Kuramoto-Sivashinsky equation, a partial differential equation used in studies of instabilities in laminar flame fronts and finally real physical data from sunspot areas in the Sun (in latitude and time) from 1874 to 2015. |
Tasks | Feature Selection |
Published | 2018-04-30 |
URL | http://arxiv.org/abs/1804.11129v1 |
http://arxiv.org/pdf/1804.11129v1.pdf | |
PWC | https://paperswithcode.com/paper/optimal-neural-network-feature-selection-for |
Repo | |
Framework | |
Syllabification by Phone Categorization
Title | Syllabification by Phone Categorization |
Authors | Jacob Krantz, Maxwell Dulin, Paul De Palma, Mark VanDam |
Abstract | Syllables play an important role in speech synthesis, speech recognition, and spoken document retrieval. A novel, low cost, and language agnostic approach to dividing words into their corresponding syllables is presented. A hybrid genetic algorithm constructs a categorization of phones optimized for syllabification. This categorization is used on top of a hidden Markov model sequence classifier to find syllable boundaries. The technique shows promising preliminary results when trained and tested on English words. |
Tasks | Speech Recognition, Speech Synthesis |
Published | 2018-07-15 |
URL | http://arxiv.org/abs/1807.05518v1 |
http://arxiv.org/pdf/1807.05518v1.pdf | |
PWC | https://paperswithcode.com/paper/syllabification-by-phone-categorization |
Repo | |
Framework | |
3D Shape Perception from Monocular Vision, Touch, and Shape Priors
Title | 3D Shape Perception from Monocular Vision, Touch, and Shape Priors |
Authors | Shaoxiong Wang, Jiajun Wu, Xingyuan Sun, Wenzhen Yuan, William T. Freeman, Joshua B. Tenenbaum, Edward H. Adelson |
Abstract | Perceiving accurate 3D object shape is important for robots to interact with the physical world. Current research along this direction has been primarily relying on visual observations. Vision, however useful, has inherent limitations due to occlusions and the 2D-3D ambiguities, especially for perception with a monocular camera. In contrast, touch gets precise local shape information, though its efficiency for reconstructing the entire shape could be low. In this paper, we propose a novel paradigm that efficiently perceives accurate 3D object shape by incorporating visual and tactile observations, as well as prior knowledge of common object shapes learned from large-scale shape repositories. We use vision first, applying neural networks with learned shape priors to predict an object’s 3D shape from a single-view color image. We then use tactile sensing to refine the shape; the robot actively touches the object regions where the visual prediction has high uncertainty. Our method efficiently builds the 3D shape of common objects from a color image and a small number of tactile explorations (around 10). Our setup is easy to apply and has potentials to help robots better perform grasping or manipulation tasks on real-world objects. |
Tasks | |
Published | 2018-08-09 |
URL | http://arxiv.org/abs/1808.03247v1 |
http://arxiv.org/pdf/1808.03247v1.pdf | |
PWC | https://paperswithcode.com/paper/3d-shape-perception-from-monocular-vision |
Repo | |
Framework | |
Analysing Symbolic Regression Benchmarks under a Meta-Learning Approach
Title | Analysing Symbolic Regression Benchmarks under a Meta-Learning Approach |
Authors | Luiz Otavio Vilas Boas Oliveira, Joao Francisco Barreto da Silva Martins, Luis Fernando Miranda, Gisele Lobo Pappa |
Abstract | The definition of a concise and effective testbed for Genetic Programming (GP) is a recurrent matter in the research community. This paper takes a new step in this direction, proposing a different approach to measure the quality of the symbolic regression benchmarks quantitatively. The proposed approach is based on meta-learning and uses a set of dataset meta-features—such as the number of examples or output skewness—to describe the datasets. Our idea is to correlate these meta-features with the errors obtained by a GP method. These meta-features define a space of benchmarks that should, ideally, have datasets (points) covering different regions of the space. An initial analysis of 63 datasets showed that current benchmarks are concentrated in a small region of this benchmark space. We also found out that number of instances and output skewness are the most relevant meta-features to GP output error. Both conclusions can help define which datasets should compose an effective testbed for symbolic regression methods. |
Tasks | Meta-Learning |
Published | 2018-05-25 |
URL | http://arxiv.org/abs/1805.10365v1 |
http://arxiv.org/pdf/1805.10365v1.pdf | |
PWC | https://paperswithcode.com/paper/analysing-symbolic-regression-benchmarks |
Repo | |
Framework | |
Two new results about quantum exact learning
Title | Two new results about quantum exact learning |
Authors | Srinivasan Arunachalam, Sourav Chakraborty, Troy Lee, Manaswi Paraashar, Ronald de Wolf |
Abstract | We present two new results about exact learning by quantum computers. First, we show how to exactly learn a $k$-Fourier-sparse $n$-bit Boolean function from $O(k^{1.5}(\log k)^2)$ uniform quantum examples for that function. This improves over the bound of $\widetilde{\Theta}(kn)$ uniformly random classical examples (Haviv and Regev, CCC’15). Our main tool is an improvement of Chang’s lemma for the special case of sparse functions. Second, we show that if a concept class $\mathcal{C}$ can be exactly learned using $Q$ quantum membership queries, then it can also be learned using $O\left(\frac{Q^2}{\log Q}\log\mathcal{C}\right)$ classical membership queries. This improves the previous-best simulation result (Servedio and Gortler, SICOMP’04) by a $\log Q$-factor. |
Tasks | |
Published | 2018-09-30 |
URL | http://arxiv.org/abs/1810.00481v2 |
http://arxiv.org/pdf/1810.00481v2.pdf | |
PWC | https://paperswithcode.com/paper/two-new-results-about-quantum-exact-learning |
Repo | |
Framework | |
Free Energy Minimization Using the 2-D Cluster Variation Method: Initial Code Verification and Validation
Title | Free Energy Minimization Using the 2-D Cluster Variation Method: Initial Code Verification and Validation |
Authors | Alianna J. Maren |
Abstract | A new approach for general artificial intelligence (GAI), building on neural network deep learning architectures, can make use of one or more hidden layers that have the ability to continuously reach a free energy minimum even after input stimulus is removed, allowing for a variety of possible behaviors. One reason that this approach has not been developed until now has been the lack of a suitable free energy equation. The Cluster Variation Method (CVM) offers a means for characterizing 2-D local pattern distributions, or configuration variables, and provides a free energy formalism in terms of these configuration variables. The equilibrium distribution of these configuration variables is defined in terms of a single interaction enthalpy parameter, h, for the case of equiprobable distribution of bistate units. For non-equiprobable distributions, the equilibrium distribution can be characterized by providing a fixed value for the fraction of units in the active state (x1), corresponding to the influence of a per-unit activation enthalpy, together with the pairwise interaction enthalpy parameter h. This paper provides verification and validation (V&V) for code that computes the configuration variable and thermodynamic values for 2-D CVM grids characterized by different interaction enthalpy parameters, or h-values. This work provides a foundation for experimenting with a 2-D CVM-based hidden layer that can, as an alternative to responding strictly to inputs, also now independently come to its own free energy minimum and also return to a free energy-minimized state after perturbations, which will enable a range of input-independent behaviors. A further use of this 2-D CVM grid is that by characterizing local patterns in terms of their corresponding h-values (together with their x1 values), we have a means for quantitatively characterizing different kinds of neural topographies. |
Tasks | |
Published | 2018-01-24 |
URL | https://arxiv.org/abs/1801.08113v2 |
https://arxiv.org/pdf/1801.08113v2.pdf | |
PWC | https://paperswithcode.com/paper/free-energy-minimization-using-the-2-d |
Repo | |
Framework | |
Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator
Title | Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator |
Authors | Jeff Zhang, Tianyu Gu, Kanad Basu, Siddharth Garg |
Abstract | Due to their growing popularity and computational cost, deep neural networks (DNNs) are being targeted for hardware acceleration. A popular architecture for DNN acceleration, adopted by the Google Tensor Processing Unit (TPU), utilizes a systolic array based matrix multiplication unit at its core. This paper deals with the design of fault-tolerant, systolic array based DNN accelerators for high defect rate technologies. To this end, we empirically show that the classification accuracy of a baseline TPU drops significantly even at extremely low fault rates (as low as $0.006%$). We then propose two novel strategies, fault-aware pruning (FAP) and fault-aware pruning+retraining (FAP+T), that enable the TPU to operate at fault rates of up to $50%$, with negligible drop in classification accuracy (as low as $0.1%$) and no run-time performance overhead. The FAP+T does introduce a one-time retraining penalty per TPU chip before it is deployed, but we propose optimizations that reduce this one-time penalty to under 12 minutes. The penalty is then amortized over the entire lifetime of the TPU’s operation. |
Tasks | |
Published | 2018-02-11 |
URL | http://arxiv.org/abs/1802.04657v2 |
http://arxiv.org/pdf/1802.04657v2.pdf | |
PWC | https://paperswithcode.com/paper/analyzing-and-mitigating-the-impact-of |
Repo | |
Framework | |
Deep Shape Analysis on Abdominal Organs for Diabetes Prediction
Title | Deep Shape Analysis on Abdominal Organs for Diabetes Prediction |
Authors | Benjamin Gutierrez-Becker, Sergios Gatidis, Daniel Gutmann, Annette Peters, Christopher Schlett Fabian Bamberg, Christian Wachinger |
Abstract | Morphological analysis of organs based on images is a key task in medical imaging computing. Several approaches have been proposed for the quantitative assessment of morphological changes, and they have been widely used for the analysis of the effects of aging, disease and other factors in organ morphology. In this work, we propose a deep neural network for predicting diabetes on abdominal shapes. The network directly operates on raw point clouds without requiring mesh processing or shape alignment. Instead of relying on hand-crafted shape descriptors, an optimal representation is learned in the end-to-end training stage of the network. For comparison, we extend the state-of-the-art shape descriptor BrainPrint to the AbdomenPrint. Our results demonstrate that the network learns shape representations that better separates healthy and diabetic individuals than traditional representations. |
Tasks | Diabetes Prediction, Morphological Analysis |
Published | 2018-08-06 |
URL | http://arxiv.org/abs/1808.01946v1 |
http://arxiv.org/pdf/1808.01946v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-shape-analysis-on-abdominal-organs-for |
Repo | |
Framework | |
Multimodal Biometric Authentication Using Choquet Integral and Genetic Algorithm
Title | Multimodal Biometric Authentication Using Choquet Integral and Genetic Algorithm |
Authors | Anouar Ben Khalifa, Sami Gazzah, Najoua Essoukri Ben Amara |
Abstract | The Choquet integral is a tool for the information fusion that is very effective in the case where fuzzy measures associated with it are well chosen. In this paper,we propose a new approach for calculating fuzzy measures associated with the Choquet integral in a context of data fusion in multimodal biometrics. The proposed approach is based on genetic algorithms. It has been validated in two databases: the first base is relative to synthetic scores and the second one is biometrically relating to the face, fingerprintand palmprint. The results achieved attest the robustness of the proposed approach. |
Tasks | |
Published | 2018-03-27 |
URL | http://arxiv.org/abs/1804.00528v1 |
http://arxiv.org/pdf/1804.00528v1.pdf | |
PWC | https://paperswithcode.com/paper/multimodal-biometric-authentication-using |
Repo | |
Framework | |
Do Outliers Ruin Collaboration?
Title | Do Outliers Ruin Collaboration? |
Authors | Mingda Qiao |
Abstract | We consider the problem of learning a binary classifier from $n$ different data sources, among which at most an $\eta$ fraction are adversarial. The overhead is defined as the ratio between the sample complexity of learning in this setting and that of learning the same hypothesis class on a single data distribution. We present an algorithm that achieves an $O(\eta n + \ln n)$ overhead, which is proved to be worst-case optimal. We also discuss the potential challenges to the design of a computationally efficient learning algorithm with a small overhead. |
Tasks | |
Published | 2018-05-12 |
URL | http://arxiv.org/abs/1805.04720v1 |
http://arxiv.org/pdf/1805.04720v1.pdf | |
PWC | https://paperswithcode.com/paper/do-outliers-ruin-collaboration |
Repo | |
Framework | |
Disambiguating fine-grained place names from descriptions by clustering
Title | Disambiguating fine-grained place names from descriptions by clustering |
Authors | Hao Chen, Maria Vasardani, Stephan Winter |
Abstract | Everyday place descriptions often contain place names of fine-grained features, such as buildings or businesses, that are more difficult to disambiguate than names referring to larger places, for example cities or natural geographic features. Fine-grained places are often significantly more frequent and more similar to each other, and disambiguation heuristics developed for larger places, such as those based on population or containment relationships, are often not applicable in these cases. In this research, we address the disambiguation of fine-grained place names from everyday place descriptions. For this purpose, we evaluate the performance of different existing clustering-based approaches, since clustering approaches require no more knowledge other than the locations of ambiguous place names. We consider not only approaches developed specifically for place name disambiguation, but also clustering algorithms developed for general data mining that could potentially be leveraged. We compare these methods with a novel algorithm, and show that the novel algorithm outperforms the other algorithms in terms of disambiguation precision and distance error over several tested datasets. |
Tasks | |
Published | 2018-08-17 |
URL | http://arxiv.org/abs/1808.05946v1 |
http://arxiv.org/pdf/1808.05946v1.pdf | |
PWC | https://paperswithcode.com/paper/disambiguating-fine-grained-place-names-from |
Repo | |
Framework | |
Efficient Counterfactual Learning from Bandit Feedback
Title | Efficient Counterfactual Learning from Bandit Feedback |
Authors | Yusuke Narita, Shota Yasui, Kohei Yata |
Abstract | What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in a wide class of estimators, achieving variance reduction relative to standard estimators. We then apply our estimators to improve advertisement design by a major advertisement company. Consistent with the theoretical result, our estimators allow us to improve on the existing bandit algorithm with more statistical confidence compared to a state-of-the-art benchmark. |
Tasks | |
Published | 2018-09-10 |
URL | http://arxiv.org/abs/1809.03084v3 |
http://arxiv.org/pdf/1809.03084v3.pdf | |
PWC | https://paperswithcode.com/paper/efficient-counterfactual-learning-from-bandit |
Repo | |
Framework | |
Model-free Tracking with Deep Appearance and Motion Features Integration
Title | Model-free Tracking with Deep Appearance and Motion Features Integration |
Authors | Xiaolong Jiang, Peizhao Li, Xiantong Zhen, Xianbin Cao |
Abstract | Being able to track an anonymous object, a model-free tracker is comprehensively applicable regardless of the target type. However, designing such a generalized framework is challenged by the lack of object-oriented prior information. As one solution, a real-time model-free object tracking approach is designed in this work relying on Convolutional Neural Networks (CNNs). To overcome the object-centric information scarcity, both appearance and motion features are deeply integrated by the proposed AMNet, which is an end-to-end offline trained two-stream network. Between the two parallel streams, the ANet investigates appearance features with a multi-scale Siamese atrous CNN, enabling the tracking-by-matching strategy. The MNet achieves deep motion detection to localize anonymous moving objects by processing generic motion features. The final tracking result at each frame is generated by fusing the output response maps from both sub-networks. The proposed AMNet reports leading performance on both OTB and VOT benchmark datasets with favorable real-time processing speed. |
Tasks | Motion Detection, Object Tracking |
Published | 2018-12-16 |
URL | http://arxiv.org/abs/1812.06418v1 |
http://arxiv.org/pdf/1812.06418v1.pdf | |
PWC | https://paperswithcode.com/paper/model-free-tracking-with-deep-appearance-and |
Repo | |
Framework | |