May 7, 2019

2718 words 13 mins read

Paper Group ANR 148

Extrapolation and learning equations. Creativity in Machine Learning. Ways of Conditioning Generative Adversarial Networks. A knowledge representation meta-model for rule-based modelling of signalling networks. Continuously Learning Neural Dialogue Management. Testing Quantum Models of Conjunction Fallacy on the World Wide Web. Large Scale Behavior …

Extrapolation and learning equations


Title	Extrapolation and learning equations
Authors	Georg Martius, Christoph H. Lampert
Abstract	In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified.
Tasks
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02995v1
PDF	http://arxiv.org/pdf/1610.02995v1.pdf
PWC	https://paperswithcode.com/paper/extrapolation-and-learning-equations
Repo
Framework

Creativity in Machine Learning


Title	Creativity in Machine Learning
Authors	Martin Thoma
Abstract	Recent machine learning techniques can be modified to produce creative results. Those results did not exist before; it is not a trivial combination of the data which was fed into the machine learning system. The obtained results come in multiple forms: As images, as text and as audio. This paper gives a high level overview of how they are created and gives some examples. It is meant to be a summary of the current work and give people who are new to machine learning some starting points.
Tasks
Published	2016-01-12
URL	http://arxiv.org/abs/1601.03642v1
PDF	http://arxiv.org/pdf/1601.03642v1.pdf
PWC	https://paperswithcode.com/paper/creativity-in-machine-learning
Repo
Framework

Ways of Conditioning Generative Adversarial Networks


Title	Ways of Conditioning Generative Adversarial Networks
Authors	Hanock Kwak, Byoung-Tak Zhang
Abstract	The GANs are generative models whose random samples realistically reflect natural images. It also can generate samples with specific attributes by concatenating a condition vector into the input, yet research on this field is not well studied. We propose novel methods of conditioning generative adversarial networks (GANs) that achieve state-of-the-art results on MNIST and CIFAR-10. We mainly introduce two models: an information retrieving model that extracts conditional information from the samples, and a spatial bilinear pooling model that forms bilinear features derived from the spatial cross product of an image and a condition vector. These methods significantly enhance log-likelihood of test data under the conditional distributions compared to the methods of concatenation.
Tasks
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01455v1
PDF	http://arxiv.org/pdf/1611.01455v1.pdf
PWC	https://paperswithcode.com/paper/ways-of-conditioning-generative-adversarial
Repo
Framework

A knowledge representation meta-model for rule-based modelling of signalling networks


Title	A knowledge representation meta-model for rule-based modelling of signalling networks
Authors	Adrien Basso-Blandin, Walter Fontana, Russ Harmer
Abstract	The study of cellular signalling pathways and their deregulation in disease states, such as cancer, is a large and extremely complex task. Indeed, these systems involve many parts and processes but are studied piecewise and their literatures and data are consequently fragmented, distributed and sometimes–at least apparently–inconsistent. This makes it extremely difficult to build significant explanatory models with the result that effects in these systems that are brought about by many interacting factors are poorly understood. The rule-based approach to modelling has shown some promise for the representation of the highly combinatorial systems typically found in signalling where many of the proteins are composed of multiple binding domains, capable of simultaneous interactions, and/or peptide motifs controlled by post-translational modifications. However, the rule-based approach requires highly detailed information about the precise conditions for each and every interaction which is rarely available from any one single source. Rather, these conditions must be painstakingly inferred and curated, by hand, from information contained in many papers–each of which contains only part of the story. In this paper, we introduce a graph-based meta-model, attuned to the representation of cellular signalling networks, which aims to ease this massive cognitive burden on the rule-based curation process. This meta-model is a generalization of that used by Kappa and BNGL which allows for the flexible representation of knowledge at various levels of granularity. In particular, it allows us to deal with information which has either too little, or too much, detail with respect to the strict rule-based meta-model. Our approach provides a basis for the gradual aggregation of fragmented biological knowledge extracted from the literature into an instance of the meta-model from which we can define an automated translation into executable Kappa programs.
Tasks
Published	2016-03-03
URL	http://arxiv.org/abs/1603.01488v1
PDF	http://arxiv.org/pdf/1603.01488v1.pdf
PWC	https://paperswithcode.com/paper/a-knowledge-representation-meta-model-for
Repo
Framework

Continuously Learning Neural Dialogue Management


Title	Continuously Learning Neural Dialogue Management
Authors	Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
Abstract	We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model’s effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model’s performance in both interactive settings, especially under higher-noise conditions.
Tasks	Dialogue Management, Spoken Dialogue Systems
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02689v1
PDF	http://arxiv.org/pdf/1606.02689v1.pdf
PWC	https://paperswithcode.com/paper/continuously-learning-neural-dialogue
Repo
Framework

Testing Quantum Models of Conjunction Fallacy on the World Wide Web


Title	Testing Quantum Models of Conjunction Fallacy on the World Wide Web
Authors	Diederik Aerts, Jonito Aerts Arguëlles, Lester Beltran, Lyneth Beltran, Massimiliano Sassoli de Bianchi, Sandro Sozzo, Tomas Veloz
Abstract	The ‘conjunction fallacy’ has been extensively debated by scholars in cognitive science and, in recent times, the discussion has been enriched by the proposal of modeling the fallacy using the quantum formalism. Two major quantum approaches have been put forward: the first assumes that respondents use a two-step sequential reasoning and that the fallacy results from the presence of ‘question order effects’; the second assumes that respondents evaluate the cognitive situation as a whole and that the fallacy results from the ‘emergence of new meanings’, as an ‘effect of overextension’ in the conceptual conjunction. Thus, the question arises as to determine whether and to what extent conjunction fallacies would result from ‘order effects’ or, instead, from ‘emergence effects’. To help clarify this situation, we propose to use the World Wide Web as an ‘information space’ that can be interrogated both in a sequential and non-sequential way, to test these two quantum approaches. We find that ‘emergence effects’, and not ‘order effects’, should be considered the main cognitive mechanism producing the observed conjunction fallacies.
Tasks
Published	2016-09-25
URL	http://arxiv.org/abs/1609.07721v2
PDF	http://arxiv.org/pdf/1609.07721v2.pdf
PWC	https://paperswithcode.com/paper/testing-quantum-models-of-conjunction-fallacy
Repo
Framework

Large Scale Behavioral Analytics via Topical Interaction


Title	Large Scale Behavioral Analytics via Topical Interaction
Authors	Shih-Chieh Su
Abstract	We propose the split-diffuse (SD) algorithm that takes the output of an existing dimension reduction algorithm, and distributes the data points uniformly across the visualization space. The result, called the topic grids, is a set of grids on various topics which are generated from the free-form text content of any domain of interest. The topic grids efficiently utilizes the visualization space to provide visual summaries for massive data. Topical analysis, comparison and interaction can be performed on the topic grids in a more perceivable way.
Tasks	Dimensionality Reduction
Published	2016-08-26
URL	http://arxiv.org/abs/1608.07625v1
PDF	http://arxiv.org/pdf/1608.07625v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-behavioral-analytics-via-topical
Repo
Framework

Motion Representation with Acceleration Images


Title	Motion Representation with Acceleration Images
Authors	Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh
Abstract	Information of time differentiation is extremely important cue for a motion representation. We have applied first-order differential velocity from a positional information, moreover we believe that second-order differential acceleration is also a significant feature in a motion representation. However, an acceleration image based on a typical optical flow includes motion noises. We have not employed the acceleration image because the noises are too strong to catch an effective motion feature in an image sequence. On one hand, the recent convolutional neural networks (CNN) are robust against input noises. In this paper, we employ acceleration-stream in addition to the spatial- and temporal-stream based on the two-stream CNN. We clearly show the effectiveness of adding the acceleration stream to the two-stream CNN.
Tasks	Optical Flow Estimation
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08395v1
PDF	http://arxiv.org/pdf/1608.08395v1.pdf
PWC	https://paperswithcode.com/paper/motion-representation-with-acceleration
Repo
Framework

Small Representations of Big Kidney Exchange Graphs


Title	Small Representations of Big Kidney Exchange Graphs
Authors	John P. Dickerson, Aleksandr M. Kazachkov, Ariel D. Procaccia, Tuomas Sandholm
Abstract	Kidney exchanges are organized markets where patients swap willing but incompatible donors. In the last decade, kidney exchanges grew from small and regional to large and national—and soon, international. This growth results in more lives saved, but exacerbates the empirical hardness of the $\mathcal{NP}$-complete problem of optimally matching patients to donors. State-of-the-art matching engines use integer programming techniques to clear fielded kidney exchanges, but these methods must be tailored to specific models and objective functions, and may fail to scale to larger exchanges. In this paper, we observe that if the kidney exchange compatibility graph can be encoded by a constant number of patient and donor attributes, the clearing problem is solvable in polynomial time. We give necessary and sufficient conditions for losslessly shrinking the representation of an arbitrary compatibility graph. Then, using real compatibility graphs from the UNOS nationwide kidney exchange, we show how many attributes are needed to encode real compatibility graphs. The experiments show that, indeed, small numbers of attributes suffice.
Tasks
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07728v2
PDF	http://arxiv.org/pdf/1605.07728v2.pdf
PWC	https://paperswithcode.com/paper/small-representations-of-big-kidney-exchange
Repo
Framework

Stacking With Auxiliary Features


Title	Stacking With Auxiliary Features
Authors	Nazneen Fatema Rajani, Raymond J. Mooney
Abstract	Ensembling methods are well known for improving prediction accuracy. However, they are limited in the sense that they cannot discriminate among component models effectively. In this paper, we propose stacking with auxiliary features that learns to fuse relevant information from multiple systems to improve performance. Auxiliary features enable the stacker to rely on systems that not just agree on an output but also the provenance of the output. We demonstrate our approach on three very different and difficult problems – the Cold Start Slot Filling, the Tri-lingual Entity Discovery and Linking and the ImageNet object detection tasks. We obtain new state-of-the-art results on the first two tasks and substantial improvements on the detection task, thus verifying the power and generality of our approach.
Tasks	Object Detection, Slot Filling
Published	2016-05-27
URL	http://arxiv.org/abs/1605.08764v1
PDF	http://arxiv.org/pdf/1605.08764v1.pdf
PWC	https://paperswithcode.com/paper/stacking-with-auxiliary-features
Repo
Framework

Edge-exchangeable graphs and sparsity (NIPS 2016)


Title	Edge-exchangeable graphs and sparsity (NIPS 2016)
Authors	Diana Cai, Trevor Campbell, Tamara Broderick
Abstract	Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We present an alternative notion of exchangeability for random graphs, which we call edge exchangeability, in which the distribution of a graph sequence is invariant to the order of the edges. We demonstrate that edge-exchangeable models, unlike models that are traditionally vertex exchangeable, can exhibit sparsity. To do so, we outline a general framework for graph generative models; by contrast to the pioneering work of Caron and Fox (2015), models within our framework are stationary across steps of the graph sequence. In particular, our model grows the graph by instantiating more latent atoms of a single random measure as the dataset size increases, rather than adding new atoms to the measure.
Tasks
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05519v2
PDF	http://arxiv.org/pdf/1612.05519v2.pdf
PWC	https://paperswithcode.com/paper/edge-exchangeable-graphs-and-sparsity-nips
Repo
Framework

Supervised and Unsupervised Ensembling for Knowledge Base Population


Title	Supervised and Unsupervised Ensembling for Knowledge Base Population
Authors	Nazneen Fatema Rajani, Raymond J. Mooney
Abstract	We present results on combining supervised and unsupervised methods to ensemble multiple systems for two popular Knowledge Base Population (KBP) tasks, Cold Start Slot Filling (CSSF) and Tri-lingual Entity Discovery and Linking (TEDL). We demonstrate that our combined system along with auxiliary features outperforms the best performing system for both tasks in the 2015 competition, several ensembling baselines, as well as the state-of-the-art stacking approach to ensembling KBP systems. The success of our technique on two different and challenging problems demonstrates the power and generality of our combined approach to ensembling.
Tasks	Knowledge Base Population, Slot Filling
Published	2016-04-16
URL	http://arxiv.org/abs/1604.04802v1
PDF	http://arxiv.org/pdf/1604.04802v1.pdf
PWC	https://paperswithcode.com/paper/supervised-and-unsupervised-ensembling-for
Repo
Framework

Domain Adaptation of Recurrent Neural Networks for Natural Language Understanding


Title	Domain Adaptation of Recurrent Neural Networks for Natural Language Understanding
Authors	Aaron Jaech, Larry Heck, Mari Ostendorf
Abstract	The goal of this paper is to use multi-task learning to efficiently scale slot filling models for natural language understanding to handle multiple target tasks or domains. The key to scalability is reducing the amount of training data needed to learn a model for a new task. The proposed multi-task model delivers better performance with less data by leveraging patterns that it learns from the other tasks. The approach supports an open vocabulary, which allows the models to generalize to unseen words, which is particularly important when very little training data is used. A newly collected crowd-sourced data set, covering four different domains, is used to demonstrate the effectiveness of the domain adaptation and open vocabulary techniques.
Tasks	Domain Adaptation, Multi-Task Learning, Slot Filling
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00117v2
PDF	http://arxiv.org/pdf/1604.00117v2.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-of-recurrent-neural
Repo
Framework

A Non-Parametric Control Chart For High Frequency Multivariate Data


Title	A Non-Parametric Control Chart For High Frequency Multivariate Data
Authors	Deovrat Kakde, Sergriy Peredriy, Arin Chaudhuri, Anya Mcguirk
Abstract	Support Vector Data Description (SVDD) is a machine learning technique used for single class classification and outlier detection. SVDD based K-chart was first introduced by Sun and Tsung for monitoring multivariate processes when underlying distribution of process parameters or quality characteristics depart from Normality. The method first trains a SVDD model on data obtained from stable or in-control operations of the process to obtain a threshold $R^2$ and kernel center a. For each new observation, its Kernel distance from the Kernel center a is calculated. The kernel distance is compared against the threshold $R^2$ to determine if the observation is within the control limits. The non-parametric K-chart provides an attractive alternative to the traditional control charts such as the Hotelling’s $T^2$ charts when distribution of the underlying multivariate data is either non-normal or is unknown. But there are challenges when K-chart is deployed in practice. The K-chart requires calculating kernel distance of each new observation but there are no guidelines on how to interpret the kernel distance plot and infer about shifts in process mean or changes in process variation. This limits the application of K-charts in big-data applications such as equipment health monitoring, where observations are generated at a very high frequency. In this scenario, the analyst using the K-chart is inundated with kernel distance results at a very high frequency, generally without any recourse for detecting presence of any assignable causes of variation. We propose a new SVDD based control chart, called as $K_T$ chart, which addresses challenges encountered when using K-chart for big-data applications. The $K_T$ charts can be used to simultaneously track process variation and central tendency. We illustrate the successful use of $K_T$ chart using the Tennessee Eastman process data.
Tasks	Outlier Detection
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07423v3
PDF	http://arxiv.org/pdf/1607.07423v3.pdf
PWC	https://paperswithcode.com/paper/a-non-parametric-control-chart-for-high
Repo
Framework

Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications


Title	Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications
Authors	Weihao Gao, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Abstract	We conduct an axiomatic study of the problem of estimating the strength of a known causal relationship between a pair of variables. We propose that an estimate of causal strength should be based on the conditional distribution of the effect given the cause (and not on the driving distribution of the cause), and study dependence measures on conditional distributions. Shannon capacity, appropriately regularized, emerges as a natural measure under these axioms. We examine the problem of calculating Shannon capacity from the observed samples and propose a novel fixed-$k$ nearest neighbor estimator, and demonstrate its consistency. Finally, we demonstrate an application to single-cell flow-cytometry, where the proposed estimators significantly reduce sample complexity.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03476v3
PDF	http://arxiv.org/pdf/1602.03476v3.pdf
PWC	https://paperswithcode.com/paper/conditional-dependence-via-shannon-capacity
Repo
Framework