October 18, 2019

2898 words 14 mins read

Paper Group ANR 639

Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks. The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning. Continual Learning Augmented Investment Decisions. Facility Locations Utility for Uncovering Classifier Overconfidence. Automatic Airway Segmentation in chest CT using Con …

Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks


Title	Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks
Authors	Ankan Kumar Bhunia, Ayan Kumar Bhunia, Prithaj Banerjee, Aishik Konwer, Abir Bhowmick, Partha Pratim Roy, Umapada Pal
Abstract	Conversion of one font to another font is very useful in real life applications. In this paper, we propose a Convolutional Recurrent Generative model to solve the word level font transfer problem. Our network is able to convert the font style of any printed text images from its current font to the required font. The network is trained end-to-end for the complete word images. Thus it eliminates the necessary pre-processing steps, like character segmentations. We extend our model to conditional setting that helps to learn one-to-many mapping function. We employ a novel convolutional recurrent model architecture in the Generator that efficiently deals with the word images of arbitrary width. It also helps to maintain the consistency of the final images after concatenating the generated image patches of target font. Besides, the Generator and the Discriminator network, we employ a Classification network to classify the generated word images of converted font style to their subsequent font categories. Most of the earlier works related to image translation are performed on square images. Our proposed architecture is the first work which can handle images of varying widths. Word images generally have varying width depending on the number of characters present. Hence, we test our model on a synthetically generated font dataset. We compare our method with some of the state-of-the-art methods for image translation. The superior performance of our network on the same dataset proves the ability of our model to learn the font distributions.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07156v3
PDF	http://arxiv.org/pdf/1801.07156v3.pdf
PWC	https://paperswithcode.com/paper/word-level-font-to-font-image-translation
Repo
Framework

The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning


Title	The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
Authors	Yang-Hui He
Abstract	We present a pedagogical introduction to the recent advances in the computational geometry, physical implications, and data science of Calabi-Yau manifolds. Aimed at the beginning research student and using Calabi-Yau spaces as an exciting play-ground, we intend to teach some mathematics to the budding physicist, some physics to the budding mathematician, and some machine-learning to both. Based on various lecture series, colloquia and seminars given by the author in the past year, this writing is a very preliminary draft of a book to appear with Springer, by whose kind permission we post to ArXiv for comments and suggestions.
Tasks
Published	2018-12-07
URL	http://arxiv.org/abs/1812.02893v1
PDF	http://arxiv.org/pdf/1812.02893v1.pdf
PWC	https://paperswithcode.com/paper/the-calabi-yau-landscape-from-geometry-to
Repo
Framework

Continual Learning Augmented Investment Decisions


Title	Continual Learning Augmented Investment Decisions
Authors	Daniel Philps, Tillman Weyde, Artur d’Avila Garcez, Roy Batchelor
Abstract	Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which is based on an explicit memory structure and a feed forward neural network (FFNN) base model and used to drive long term financial investment decisions. We demonstrate that our approach improves accuracy in investment decision making while memory is addressed in an explainable way. Our approach introduces novel remember cues, consisting of empirically learned change points in the absolute error series of the FFNN. Memory recall is also novel, with contextual similarity assessed over time by sampling distances using dynamic time warping (DTW). We demonstrate the benefits of our approach by using it in an expected return forecasting task to drive investment decisions. In an investment simulation in a broad international equity universe between 2003-2017, our approach significantly outperforms FFNN base models. We also illustrate how CLA’s memory addressing works in practice, using a worked example to demonstrate the explainability of our approach.
Tasks	Continual Learning, Decision Making
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02340v4
PDF	http://arxiv.org/pdf/1812.02340v4.pdf
PWC	https://paperswithcode.com/paper/continual-learning-augmented-investment
Repo
Framework

Facility Locations Utility for Uncovering Classifier Overconfidence


Title	Facility Locations Utility for Uncovering Classifier Overconfidence
Authors	Karsten Maurer, Walter Bennette
Abstract	Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most information about the classifier’s predictive characteristics. Previous works have focused on developing utility models and query algorithms for discovering unknown unknowns — misclassifications with a predictive confidence above some arbitrary threshold. However, if misclassifications occur at the rate reflected by the confidence values, then these search methods reveal nothing more than a proper assessment of predictive certainty. We are unable to properly mitigate the risks associated with model deficiency when the model’s confidence in prediction exceeds the actual model accuracy. We propose a facility locations utility model and corresponding greedy query algorithm that instead searches for overconfident unknown unknowns. Through robust empirical experiments we demonstrate that the greedy query algorithm with the facility locations utility model consistently results in oracle queries with superior performance in discovering overconfident unknown unknowns than previous methods.
Tasks
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05571v1
PDF	http://arxiv.org/pdf/1810.05571v1.pdf
PWC	https://paperswithcode.com/paper/facility-locations-utility-for-uncovering
Repo
Framework

Automatic Airway Segmentation in chest CT using Convolutional Neural Networks


Title	Automatic Airway Segmentation in chest CT using Convolutional Neural Networks
Authors	A. Garcia-Uceda Juarez, H. A. W. M. Tiddens, M. de Bruijne
Abstract	Segmentation of the airway tree from chest computed tomography (CT) images is critical for quantitative assessment of airway diseases including bronchiectasis and chronic obstructive pulmonary disease (COPD). However, obtaining an accurate segmentation of airways from CT scans is difficult due to the high complexity of airway structures. Recently, deep convolutional neural networks (CNNs) have become the state-of-the-art for many segmentation tasks, and in particular the so-called Unet architecture for biomedical images. However, its application to the segmentation of airways still remains a challenging task. This work presents a simple but robust approach based on a 3D Unet to perform segmentation of airways from chest CTs. The method is trained on a dataset composed of 12 CTs, and tested on another 6 CTs. We evaluate the influence of different loss functions and data augmentation techniques, and reach an average dice coefficient of 0.8 between the ground-truth and our automated segmentations.
Tasks	Computed Tomography (CT), Data Augmentation
Published	2018-08-14
URL	http://arxiv.org/abs/1808.04576v1
PDF	http://arxiv.org/pdf/1808.04576v1.pdf
PWC	https://paperswithcode.com/paper/automatic-airway-segmentation-in-chest-ct
Repo
Framework

Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks


Title	Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks
Authors	Liang Yao, Chengsheng Mao, Yuan Luo
Abstract	Clinical text classification is an important problem in medical natural language processing. Existing studies have conventionally focused on rules or knowledge sources-based feature engineering, but only a few have exploited effective feature learning capability of deep learning methods. In this study, we propose a novel approach which combines rule-based features and knowledge-guided deep learning techniques for effective disease classification. Critical Steps of our method include identifying trigger phrases, predicting classes with very few examples using trigger phrases and training a convolutional neural network with word embeddings and Unified Medical Language System (UMLS) entity embeddings. We evaluated our method on the 2008 Integrating Informatics with Biology and the Bedside (i2b2) obesity challenge. The results show that our method outperforms the state of the art methods.
Tasks	Entity Embeddings, Feature Engineering, Text Classification, Word Embeddings
Published	2018-07-17
URL	http://arxiv.org/abs/1807.07425v2
PDF	http://arxiv.org/pdf/1807.07425v2.pdf
PWC	https://paperswithcode.com/paper/clinical-text-classification-with-rule-based
Repo
Framework

Using Poisson Binomial GLMs to Reveal Voter Preferences


Title	Using Poisson Binomial GLMs to Reveal Voter Preferences
Authors	Evan Rosenman, Nitin Viswanathan
Abstract	We present a new modeling technique for solving the problem of ecological inference, in which individual-level associations are inferred from labeled data available only at the aggregate level. We model aggregate count data as arising from the Poisson binomial, the distribution of the sum of independent but not identically distributed Bernoulli random variables. We relate individual-level probabilities to individual covariates using both a logistic regression and a neural network. A normal approximation is derived via the Lyapunov Central Limit Theorem, allowing us to efficiently fit these models on large datasets. We apply this technique to the problem of revealing voter preferences in the 2016 presidential election, fitting a model to a sample of over four million voters from the highly contested swing state of Pennsylvania. We validate the model at the precinct level via a holdout set, and at the individual level using weak labels, finding that the model is predictive and it learns intuitively reasonable associations.
Tasks
Published	2018-02-04
URL	http://arxiv.org/abs/1802.01053v1
PDF	http://arxiv.org/pdf/1802.01053v1.pdf
PWC	https://paperswithcode.com/paper/using-poisson-binomial-glms-to-reveal-voter
Repo
Framework

Fast and scalable learning of neuro-symbolic representations of biomedical knowledge


Title	Fast and scalable learning of neuro-symbolic representations of biomedical knowledge
Authors	Asan Agibetov, Matthias Samwald
Abstract	In this work we address the problem of fast and scalable learning of neuro-symbolic representations for general biological knowledge. Based on a recently published comprehensive biological knowledge graph (Alshahrani, 2017) that was used for demonstrating neuro-symbolic representation learning, we show how to train fast (under 1 minute) log-linear neural embeddings of the entities. We utilize these representations as inputs for machine learning classifiers to enable important tasks such as biological link prediction. Classifiers are trained by concatenating learned entity embeddings to represent entity relations, and training classifiers on the concatenated embeddings to discern true relations from automatically generated negative examples. Our simple embedding methodology greatly improves on classification error compared to previously published state-of-the-art results, yielding a maximum increase of $+0.28$ F-measure and $+0.22$ ROC AUC scores for the most difficult biological link prediction problem. Finally, our embedding approach is orders of magnitude faster to train ($\leq$ 1 minute vs. hours), much more economical in terms of embedding dimensions ($d=50$ vs. $d=512$), and naturally encodes the directionality of the asymmetric biological relations, that can be controlled by the order with which we concatenate the embeddings.
Tasks	Entity Embeddings, Link Prediction, Representation Learning
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11105v1
PDF	http://arxiv.org/pdf/1804.11105v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-scalable-learning-of-neuro-symbolic
Repo
Framework

Factorising AMR generation through syntax


Title	Factorising AMR generation through syntax
Authors	Kris Cao, Stephen Clark
Abstract	Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down generating from AMR into two steps: first generate a syntactic structure, and then generate the surface form. We show that decomposing the generation process this way leads to state-of-the-art single model performance generating from AMR without additional unlabelled data. We also demonstrate that we can generate meaning-preserving syntactic paraphrases of the same AMR graph, as judged by humans.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07707v2
PDF	http://arxiv.org/pdf/1804.07707v2.pdf
PWC	https://paperswithcode.com/paper/generating-syntactically-varied-realisations
Repo
Framework

Active Community Detection with Maximal Expected Model Change


Title	Active Community Detection with Maximal Expected Model Change
Authors	Dan Kushnir, Benjamin Mirabelli
Abstract	We present a novel active learning algorithm for community detection on networks. Our proposed algorithm uses a Maximal Expected Model Change (MEMC) criterion for querying network nodes label assignments. MEMC detects nodes that maximally change the community assignment likelihood model following a query. Our method is inspired by detection in the benchmark Stochastic Block Model (SBM), where we provide sample complexity analysis and empirical study with SBM and real network data for binary as well as for the multi-class settings. The analysis also covers the most challenging case of sparse degree and below-detection-threshold SBMs, where we observe a super-linear error reduction. MEMC is shown to be superior to the random selection baseline and other state-of-the-art active learners.
Tasks	Active Learning, Community Detection
Published	2018-01-11
URL	https://arxiv.org/abs/1801.05856v2
PDF	https://arxiv.org/pdf/1801.05856v2.pdf
PWC	https://paperswithcode.com/paper/active-community-detection-a-maximum
Repo
Framework

State representation learning with recurrent capsule networks


Title	State representation learning with recurrent capsule networks
Authors	Louis Annabi, Michael Garcia Ortiz
Abstract	Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by trying to predict the future observations in an agent’s trajectory.
Tasks	Representation Learning
Published	2018-12-28
URL	http://arxiv.org/abs/1812.11202v4
PDF	http://arxiv.org/pdf/1812.11202v4.pdf
PWC	https://paperswithcode.com/paper/state-representation-learning-with-recurrent
Repo
Framework

Optimization Algorithm Inspired Deep Neural Network Structure Design


Title	Optimization Algorithm Inspired Deep Neural Network Structure Design
Authors	Huan Li, Yibo Yang, Dongmin Chen, Zhouchen Lin
Abstract	Deep neural networks have been one of the dominant machine learning approaches in recent years. Several new network structures are proposed and have better performance than the traditional feedforward neural network structure. Representative ones include the skip connection structure in ResNet and the dense connection structure in DenseNet. However, it still lacks a unified guidance for the neural network structure design. In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network structure. Specifically, we prove that the propagation in the feedforward neural network with the same linear transformation in different layers is equivalent to minimizing some function using the gradient descent algorithm. Based on this observation, we replace the gradient descent algorithm with the heavy ball algorithm and Nesterov’s accelerated gradient descent algorithm, which are faster and inspire us to design new and better network structures. ResNet and DenseNet can be considered as two special cases of our framework. Numerical experiments on CIFAR-10, CIFAR-100 and ImageNet verify the advantage of our optimization algorithm inspired structures over ResNet and DenseNet.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01638v1
PDF	http://arxiv.org/pdf/1810.01638v1.pdf
PWC	https://paperswithcode.com/paper/optimization-algorithm-inspired-deep-neural
Repo
Framework

Robust Bregman Clustering


Title	Robust Bregman Clustering
Authors	Claire Brécheteau, Aurélie Fischer, Clément Levrard
Abstract	Using a trimming approach, we investigate a k-means type method based on Bregman divergences for clustering data possibly corrupted with clutter noise. The main interest of Bregman divergences is that the standard Lloyd algorithm adapts to these distortion measures, and they are well-suited for clustering data sampled according to mixture models from exponential families. We prove that there exists an optimal codebook, and that an empirically optimal codebook converges a.s. to an optimal codebook in the distortion sense. Moreover, we obtain the sub-Gaussian rate of convergence for k-means 1 $\sqrt$ n under mild tail assumptions. Also, we derive a Lloyd-type algorithm with a trimming parameter that can be selected from data according to some heuristic, and present some experimental results.
Tasks
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04356v1
PDF	http://arxiv.org/pdf/1812.04356v1.pdf
PWC	https://paperswithcode.com/paper/robust-bregman-clustering
Repo
Framework

Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks


Title	Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks
Authors	Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya, Muhammad Zeshan Afzal, Marcus Liwicki
Abstract	This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents. The handwritten annotations can appear in form of underlines and text by using various writing instruments, e.g., the use of pencils makes the data more challenging. We train and evaluate various end-to-end semantic segmentation approaches and report the results. The task is to classify the pixels of documents into two classes: background and handwritten annotation. The best model achieves a mean Intersection over Union (IoU) score of 95.6% on the test documents of the presented dataset. We also present a comparison of different strategies used for data augmentation and training on our presented dataset. For evaluation, we use the Layout Analysis Evaluator for the ICDAR 2017 Competition on Layout Analysis for Challenging Medieval Manuscripts.
Tasks	Data Augmentation, Semantic Segmentation
Published	2018-04-01
URL	http://arxiv.org/abs/1804.00236v2
PDF	http://arxiv.org/pdf/1804.00236v2.pdf
PWC	https://paperswithcode.com/paper/recognizing-challenging-handwritten
Repo
Framework

On the Algorithmic Power of Spiking Neural Networks


Title	On the Algorithmic Power of Spiking Neural Networks
Authors	Chi-Ning Chou, Kai-Min Chung, Chi-Jen Lu
Abstract	Spiking Neural Networks (SNN) are mathematical models in neuroscience to describe the dynamics among a set of neurons that interact with each other by firing instantaneous signals, a.k.a., spikes. Interestingly, a recent advance in neuroscience [Barrett-Den`eve-Machens, NIPS 2013] showed that the neurons’ firing rate, i.e., the average number of spikes fired per unit of time, can be characterized by the optimal solution of a quadratic program defined by the parameters of the dynamics. This indicated that SNN potentially has the computational power to solve non-trivial quadratic programs. However, the results were justified empirically without rigorous analysis. We put this into the context of natural algorithms and aim to investigate the algorithmic power of SNN. Especially, we emphasize on giving rigorous asymptotic analysis on the performance of SNN in solving optimization problems. To enforce a theoretical study, we first identify a simplified SNN model that is tractable for analysis. Next, we confirm the empirical observation in the work of Barrett et al. by giving an upper bound on the convergence rate of SNN in solving the quadratic program. Further, we observe that in the case where there are infinitely many optimal solutions, SNN tends to converge to the one with smaller l1 norm. We give an affirmative answer to our finding by showing that SNN can solve the l1 minimization problem under some regular conditions. Our main technical insight is a dual view of the SNN dynamics, under which SNN can be viewed as a new natural primal-dual algorithm for the l1 minimization problem. We believe that the dual view is of independent interest and may potentially find interesting interpretation in neuroscience.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10375v2
PDF	http://arxiv.org/pdf/1803.10375v2.pdf
PWC	https://paperswithcode.com/paper/on-the-algorithmic-power-of-spiking-neural
Repo
Framework