Paper Group ANR 141
Massively Parallel Video Networks. How do you correct run-on sentences it’s not as easy as it seems. Analysis of Extremely Obese Individuals Using Deep Learning Stacked Autoencoders and Genome-Wide Genetic Data. On Attention Modules for Audio-Visual Synchronization. Interpretable Visual Question Answering by Reasoning on Dependency Trees. DeGroot-F …
Massively Parallel Video Networks
| Title | Massively Parallel Video Networks |
| Authors | Joao Carreira, Viorica Patraucean, Laurent Mazare, Andrew Zisserman, Simon Osindero |
| Abstract | We introduce a class of causal video understanding models that aims to improve efficiency of video processing by maximising throughput, minimising latency, and reducing the number of clock cycles. Leveraging operation pipelining and multi-rate clocks, these models perform a minimal amount of computation (e.g. as few as four convolutional layers) for each frame per timestep to produce an output. The models are still very deep, with dozens of such operations being performed but in a pipelined fashion that enables depth-parallel computation. We illustrate the proposed principles by applying them to existing image architectures and analyse their behaviour on two video tasks: action recognition and human keypoint localisation. The results show that a significant degree of parallelism, and implicitly speedup, can be achieved with little loss in performance. |
| Tasks | Temporal Action Localization, Video Understanding |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.03863v2 |
| http://arxiv.org/pdf/1806.03863v2.pdf | |
| PWC | https://paperswithcode.com/paper/massively-parallel-video-networks |
| Repo | |
| Framework | |
How do you correct run-on sentences it’s not as easy as it seems
| Title | How do you correct run-on sentences it’s not as easy as it seems |
| Authors | Junchao Zheng, Courtney Napoles, Joel Tetreault, Kostiantyn Omelianchuk |
| Abstract | Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and whole-sentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discuss implications for correcting run-ons and other types of mistakes that have low coverage in error-annotated corpora. |
| Tasks | Grammatical Error Correction |
| Published | 2018-09-21 |
| URL | http://arxiv.org/abs/1809.08298v1 |
| http://arxiv.org/pdf/1809.08298v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-do-you-correct-run-on-sentences-its-not |
| Repo | |
| Framework | |
Analysis of Extremely Obese Individuals Using Deep Learning Stacked Autoencoders and Genome-Wide Genetic Data
| Title | Analysis of Extremely Obese Individuals Using Deep Learning Stacked Autoencoders and Genome-Wide Genetic Data |
| Authors | Casimiro A. Curbelo Montañez, Paul Fergus, Carl Chalmers, Jade Hind |
| Abstract | The aetiology of polygenic obesity is multifactorial, which indicates that life-style and environmental factors may influence multiples genes to aggravate this disorder. Several low-risk single nucleotide polymorphisms (SNPs) have been associated with BMI. However, identified loci only explain a small proportion of the variation ob-served for this phenotype. The linear nature of genome wide association studies (GWAS) used to identify associations between genetic variants and the phenotype have had limited success in explaining the heritability variation of BMI and shown low predictive capacity in classification studies. GWAS ignores the epistatic interactions that less significant variants have on the phenotypic outcome. In this paper we utilise a novel deep learning-based methodology to reduce the high dimensional space in GWAS and find epistatic interactions between SNPs for classification purposes. SNPs were filtered based on the effects associations have with BMI. Since Bonferroni adjustment for multiple testing is highly conservative, an important proportion of SNPs involved in SNP-SNP interactions are ignored. Therefore, only SNPs with p-values < 1x10-2 were considered for subsequent epistasis analysis using stacked auto encoders (SAE). This allows the nonlinearity present in SNP-SNP interactions to be discovered through progressively smaller hidden layer units and to initialise a multi-layer feedforward artificial neural network (ANN) classifier. The classifier is fine-tuned to classify extremely obese and non-obese individuals. The best results were obtained with 2000 compressed units (SE=0.949153, SP=0.933014, Gini=0.949936, Lo-gloss=0.1956, AUC=0.97497 and MSE=0.054057). Using 50 compressed units it was possible to achieve (SE=0.785311, SP=0.799043, Gini=0.703566, Logloss=0.476864, AUC=0.85178 and MSE=0.156315). |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.06262v2 |
| http://arxiv.org/pdf/1804.06262v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-extremely-obese-individuals-using |
| Repo | |
| Framework | |
On Attention Modules for Audio-Visual Synchronization
| Title | On Attention Modules for Audio-Visual Synchronization |
| Authors | Naji Khosravan, Shervin Ardeshir, Rohit Puri |
| Abstract | With the development of media and networking technologies, multimedia applications ranging from feature presentation in a cinema setting to video on demand to interactive video conferencing are in great demand. Good synchronization between audio and video modalities is a key factor towards defining the quality of a multimedia presentation. The audio and visual signals of a multimedia presentation are commonly managed by independent workflows - they are often separately authored, processed, stored and even delivered to the playback system. This opens up the possibility of temporal misalignment between the two modalities - such a tendency is often more pronounced in the case of produced content (such as movies). To judge whether audio and video signals of a multimedia presentation are synchronized, we as humans often pay close attention to discriminative spatio-temporal blocks of the video (e.g. synchronizing the lip movement with the utterance of words, or the sound of a bouncing ball at the moment it hits the ground). At the same time, we ignore large portions of the video in which no discriminative sounds exist (e.g. background music playing in a movie). Inspired by this observation, we study leveraging attention modules for automatically detecting audio-visual synchronization. We propose neural network based attention modules, capable of weighting different portions (spatio-temporal blocks) of the video based on their respective discriminative power. Our experiments indicate that incorporating attention modules yields state-of-the-art results for the audio-visual synchronization classification problem. |
| Tasks | Audio-Visual Synchronization |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.06071v1 |
| http://arxiv.org/pdf/1812.06071v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-attention-modules-for-audio-visual |
| Repo | |
| Framework | |
Interpretable Visual Question Answering by Reasoning on Dependency Trees
| Title | Interpretable Visual Question Answering by Reasoning on Dependency Trees |
| Authors | Qingxing Cao, Bailin Li, Xiaodan Liang, Liang Lin |
| Abstract | Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent studies have attempted to use explicit compositional processes to assemble multiple subtasks embedded in questions, their models heavily rely on annotations or handcrafted rules to obtain valid reasoning processes, which leads to either heavy workloads or poor performance on compositional reasoning. In this paper, to better align image and language domains in diverse and unrestricted cases, we propose a novel neural network model that performs global reasoning on a dependency tree parsed from the question; thus, our model is called a parse-tree-guided reasoning network (PTGRN). This network consists of three collaborative modules: i) an attention module that exploits the local visual evidence of each word parsed from the question, ii) a gated residual composition module that composes the previously mined evidence, and iii) a parse-tree-guided propagation module that passes the mined evidence along the parse tree. Thus, PTGRN is capable of building an interpretable visual question answering (VQA) system that gradually derives image cues following question-driven parse-tree reasoning. Experiments on relational datasets demonstrate the superiority of PTGRN over current state-of-the-art VQA methods, and the visualization results highlight the explainable capability of our reasoning system. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2018-09-06 |
| URL | https://arxiv.org/abs/1809.01810v2 |
| https://arxiv.org/pdf/1809.01810v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-visual-question-answering-by |
| Repo | |
| Framework | |
DeGroot-Friedkin Map in Opinion Dynamics is Mirror Descent
| Title | DeGroot-Friedkin Map in Opinion Dynamics is Mirror Descent |
| Authors | Abhishek Halder |
| Abstract | We provide a variational interpretation of the DeGroot-Friedkin map in opinion dynamics. Specifically, we show that the nonlinear dynamics for the DeGroot-Friedkin map can be viewed as mirror descent on the standard simplex with the associated Bregman divergence being equal to the generalized Kullback-Leibler divergence, i.e., an entropic mirror descent. Our results reveal that the DeGroot-Friedkin map elicits an individual’s social power to be close to her social influence while minimizing the so called “extropy” – the entropy of the complimentary opinion. |
| Tasks | |
| Published | 2018-12-29 |
| URL | http://arxiv.org/abs/1812.11293v3 |
| http://arxiv.org/pdf/1812.11293v3.pdf | |
| PWC | https://paperswithcode.com/paper/degroot-friedkin-map-in-opinion-dynamics-is |
| Repo | |
| Framework | |
Random Projection in Deep Neural Networks
| Title | Random Projection in Deep Neural Networks |
| Authors | Piotr Iwo Wójcik |
| Abstract | This work investigates the ways in which deep learning methods can benefit from random projection (RP), a classic linear dimensionality reduction method. We focus on two areas where, as we have found, employing RP techniques can improve deep models: training neural networks on high-dimensional data and initialization of network parameters. Training deep neural networks (DNNs) on sparse, high-dimensional data with no exploitable structure implies a network architecture with an input layer that has a huge number of weights, which often makes training infeasible. We show that this problem can be solved by prepending the network with an input layer whose weights are initialized with an RP matrix. We propose several modifications to the network architecture and training regime that makes it possible to efficiently train DNNs with learnable RP layer on data with as many as tens of millions of input features and training examples. In comparison to the state-of-the-art methods, neural networks with RP layer achieve competitive performance or improve the results on several extremely high-dimensional real-world datasets. The second area where the application of RP techniques can be beneficial for training deep models is weight initialization. Setting the initial weights in DNNs to elements of various RP matrices enabled us to train residual deep networks to higher levels of performance. |
| Tasks | Dimensionality Reduction |
| Published | 2018-12-22 |
| URL | http://arxiv.org/abs/1812.09489v1 |
| http://arxiv.org/pdf/1812.09489v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-projection-in-deep-neural-networks |
| Repo | |
| Framework | |
Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
| Title | Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN) |
| Authors | Shabab Bazrafkan, Hossein Javidnia, Peter Corcoran |
| Abstract | One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. In this work, a new framework is presented to train a deep conditional generator by placing a classifier in parallel with the discriminator and back propagate the classification error through the generator network. The method is versatile and is applicable to any variations of Generative Adversarial Network (GAN) implementation, and also gives superior results compared to similar methods. |
| Tasks | |
| Published | 2018-05-01 |
| URL | http://arxiv.org/abs/1805.00316v3 |
| http://arxiv.org/pdf/1805.00316v3.pdf | |
| PWC | https://paperswithcode.com/paper/versatile-auxiliary-classifier-with-1 |
| Repo | |
| Framework | |
Bayesian graph convolutional neural networks for semi-supervised classification
| Title | Bayesian graph convolutional neural networks for semi-supervised classification |
| Authors | Yingxue Zhang, Soumyasundar Pal, Mark Coates, Deniz Üstebay |
| Abstract | Recently, techniques for applying convolutional neural networks to graph-structured data have emerged. Graph convolutional neural networks (GCNNs) have been used to address node and graph classification and matrix completion. Although the performance has been impressive, the current implementations have limited capability to incorporate uncertainty in the graph structure. Almost all GCNNs process a graph as though it is a ground-truth depiction of the relationship between nodes, but often the graphs employed in applications are themselves derived from noisy data or modelling assumptions. Spurious edges may be included; other edges may be missing between nodes that have very strong relationships. In this paper we adopt a Bayesian approach, viewing the observed graph as a realization from a parametric family of random graphs. We then target inference of the joint posterior of the random graph parameters and the node (or graph) labels. We present the Bayesian GCNN framework and develop an iterative learning procedure for the case of assortative mixed-membership stochastic block models. We present the results of experiments that demonstrate that the Bayesian formulation can provide better performance when there are very few labels available during the training process. |
| Tasks | Graph Classification, Matrix Completion |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11103v1 |
| http://arxiv.org/pdf/1811.11103v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-graph-convolutional-neural-networks |
| Repo | |
| Framework | |
Binary Compressive Sensing via Smoothed $\ell_0$ Gradient Descent
| Title | Binary Compressive Sensing via Smoothed $\ell_0$ Gradient Descent |
| Authors | Tianlin Liu, Dae Gwan Lee |
| Abstract | We present a Compressive Sensing algorithm for reconstructing binary signals from its linear measurements. The proposed algorithm minimizes a non-convex cost function expressed as a weighted sum of smoothed $\ell_0$ norms which takes into account the binariness of signals. We show that for binary signals the proposed algorithm outperforms other existing algorithms in recovery rate while requiring a short run time. |
| Tasks | Compressive Sensing |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.09937v2 |
| http://arxiv.org/pdf/1801.09937v2.pdf | |
| PWC | https://paperswithcode.com/paper/binary-compressive-sensing-via-smoothed-ell_0 |
| Repo | |
| Framework | |
Smoothed Online Optimization for Regression and Control
| Title | Smoothed Online Optimization for Regression and Control |
| Authors | Gautam Goel, Adam Wierman |
| Abstract | We consider Online Convex Optimization (OCO) in the setting where the costs are $m$-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio $3 + O(1/m)$, irrespective of the ambient dimension. Additionally, we show that when the sequence of cost functions is $\epsilon$-smooth, OBD has near-optimal dynamic regret and maintains strong per-round accuracy. We demonstrate the generality of our approach by showing that the OBD framework can be used to construct competitive algorithms for a variety of online problems across learning and control, including online variants of ridge regression, logistic regression, maximum likelihood estimation, and LQR control. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.10132v2 |
| http://arxiv.org/pdf/1810.10132v2.pdf | |
| PWC | https://paperswithcode.com/paper/smoothed-online-optimization-for-regression |
| Repo | |
| Framework | |
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
| Title | Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version) |
| Authors | Weiran Huang, Jungseul Ok, Liang Li, Wei Chen |
| Abstract | We study the Combinatorial Pure Exploration problem with Continuous and Separable reward functions (CPE-CS) in the stochastic multi-armed bandit setting. In a CPE-CS instance, we are given several stochastic arms with unknown distributions, as well as a collection of possible decisions. Each decision has a reward according to the distributions of arms. The goal is to identify the decision with the maximum reward, using as few arm samples as possible. The problem generalizes the combinatorial pure exploration problem with linear rewards, which has attracted significant attention in recent years. In this paper, we propose an adaptive learning algorithm for the CPE-CS problem, and analyze its sample complexity. In particular, we introduce a new hardness measure called the consistent optimality hardness, and give both the upper and lower bounds of sample complexity. Moreover, we give examples to demonstrate that our solution has the capacity to deal with non-linear reward functions. |
| Tasks | |
| Published | 2018-05-04 |
| URL | http://arxiv.org/abs/1805.01685v1 |
| http://arxiv.org/pdf/1805.01685v1.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-pure-exploration-with |
| Repo | |
| Framework | |
A Talker Ensemble: the University of Wrocław’s Entry to the NIPS 2017 Conversational Intelligence Challenge
| Title | A Talker Ensemble: the University of Wrocław’s Entry to the NIPS 2017 Conversational Intelligence Challenge |
| Authors | Jan Chorowski, Adrian Łańcucki, Szymon Malik, Maciej Pawlikowski, Paweł Rychlikowski, Paweł Zykowski |
| Abstract | We present Poetwannabe, a chatbot submitted by the University of Wroc{\l}aw to the NIPS 2017 Conversational Intelligence Challenge, in which it ranked first ex-aequo. It is able to conduct a conversation with a user in a natural language. The primary functionality of our dialogue system is context-aware question answering (QA), while its secondary function is maintaining user engagement. The chatbot is composed of a number of sub-modules, which independently prepare replies to user’s prompts and assess their own confidence. To answer questions, our dialogue system relies heavily on factual data, sourced mostly from Wikipedia and DBpedia, data of real user interactions in public forums, as well as data concerning general literature. Where applicable, modules are trained on large datasets using GPUs. However, to comply with the competition’s requirements, the final system is compact and runs on commodity hardware. |
| Tasks | Chatbot, Question Answering |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08032v1 |
| http://arxiv.org/pdf/1805.08032v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-talker-ensemble-the-university-of-wrocaws |
| Repo | |
| Framework | |
Cognitive Consistency Routing Algorithm of Capsule-network
| Title | Cognitive Consistency Routing Algorithm of Capsule-network |
| Authors | Huayu Li |
| Abstract | Artificial Neural Networks (ANNs) are computational models inspired by the central nervous system (especially the brain) of animals and are used to estimate or generate unknown approximation functions relied on large amounts of inputs. Capsule Neural Network (Sabour S, et al.[2017]) is a novel structure of Convolutional Neural Networks which simulates the visual processing system of human brain. In this paper, we introduce psychological theories which called Cognitive Consistency to optimize the routing algorithm of Capsnet to make it more close to the work pattern of human brain. It has been shown in the experiment that a progress had been made compared with the baseline. |
| Tasks | |
| Published | 2018-08-27 |
| URL | http://arxiv.org/abs/1808.09062v3 |
| http://arxiv.org/pdf/1808.09062v3.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-consistency-routing-algorithm-of |
| Repo | |
| Framework | |
Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates
| Title | Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates |
| Authors | Yining Wang, Sivaraman Balakrishnan, Aarti Singh |
| Abstract | We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has access to zeroth-order information). Optimization performance is evaluated by the expected difference of function values at the estimated optimum and the true optimum. In contrast to the classical optimization setup, first-order information like gradients are not directly accessible to the optimization algorithm. We show that the classical minimax framework of analysis, which roughly characterizes the worst-case query complexity of an optimization algorithm in this setting, leads to excessively pessimistic results. We propose a local minimax framework to study the fundamental difficulty of optimizing smooth functions with adaptive function evaluations, which provides a refined picture of the intrinsic difficulty of zeroth-order optimization. We show that for functions with fast level set growth around the global minimum, carefully designed optimization algorithms can identify a near global minimizer with many fewer queries. For the special case of strongly convex and smooth functions, our implied convergence rates match the ones developed for zeroth-order convex optimization problems. At the other end of the spectrum, for worst-case smooth functions no algorithm can converge faster than the minimax rate of estimating the entire unknown function in the $\ell_\infty$-norm. We provide an intuitive and efficient algorithm that attains the derived upper error bounds. |
| Tasks | |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08586v1 |
| http://arxiv.org/pdf/1803.08586v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-of-smooth-functions-with-noisy |
| Repo | |
| Framework | |
