Paper Group ANR 402
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks. The effect of the choice of neural network depth and breadth on the size of its hypothesis space. Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization. Unsupervised Part-of-Speech Induction. PeSOA: Pe …
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
| Title | Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks |
| Authors | Yonatan Belinkov, Lluís Màrquez, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass |
| Abstract | While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially with higher quality NMT models. |
| Tasks | Machine Translation, Part-Of-Speech Tagging, Representation Learning |
| Published | 2018-01-23 |
| URL | http://arxiv.org/abs/1801.07772v1 |
| http://arxiv.org/pdf/1801.07772v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-layers-of-representation-in-neural |
| Repo | |
| Framework | |
The effect of the choice of neural network depth and breadth on the size of its hypothesis space
| Title | The effect of the choice of neural network depth and breadth on the size of its hypothesis space |
| Authors | Lech Szymanski, Brendan McCane, Michael Albert |
| Abstract | We show that the number of unique function mappings in a neural network hypothesis space is inversely proportional to $\prod_lU_l!$, where $U_{l}$ is the number of neurons in the hidden layer $l$. |
| Tasks | |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.02460v1 |
| http://arxiv.org/pdf/1806.02460v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effect-of-the-choice-of-neural-network |
| Repo | |
| Framework | |
Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
| Title | Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization |
| Authors | Apratim Bhattacharyya, Mario Fritz, Bernt Schiele |
| Abstract | For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem can be formalized as a sequence prediction problem, where a number of observations are used to predict the sequence into the future. However, real-world scenarios demand a model of uncertainty of such predictions, as future states become increasingly uncertain and multi-modal – in particular on long time horizons. This makes modelling and learning challenging. We cast state of the art semantic segmentation and future prediction models based on deep learning into a Bayesian formulation that in turn allows for a full Bayesian treatment of the prediction problem. We present a new sampling scheme for this model that draws from the success of variational autoencoders by incorporating a recognition network. In the experiments we show that our model outperforms prior work in accuracy of the predicted segmentation and provides calibrated probabilities that also better capture the multi-modal aspects of possible future states of street scenes. |
| Tasks | Future prediction, Semantic Segmentation |
| Published | 2018-06-18 |
| URL | http://arxiv.org/abs/1806.06939v2 |
| http://arxiv.org/pdf/1806.06939v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-prediction-of-future-street-scenes |
| Repo | |
| Framework | |
Unsupervised Part-of-Speech Induction
| Title | Unsupervised Part-of-Speech Induction |
| Authors | Omid Kashefi |
| Abstract | Part-of-Speech (POS) tagging is an old and fundamental task in natural language processing. While supervised POS taggers have shown promising accuracy, it is not always feasible to use supervised methods due to lack of labeled data. In this project, we attempt to unsurprisingly induce POS tags by iteratively looking for a recurring pattern of words through a hierarchical agglomerative clustering process. Our approach shows promising results when compared to the tagging results of the state-of-the-art unsupervised POS taggers. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2018-01-10 |
| URL | http://arxiv.org/abs/1801.03564v1 |
| http://arxiv.org/pdf/1801.03564v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-part-of-speech-induction |
| Repo | |
| Framework | |
PeSOA: Penguins Search Optimisation Algorithm for Global Optimisation Problems
| Title | PeSOA: Penguins Search Optimisation Algorithm for Global Optimisation Problems |
| Authors | Youcef Gheraibia, Abdelouahab Moussaoui, Peng-Yeng Yin, Yiannis Papadopoulos, Smaine Maazouzi |
| Abstract | This paper develops Penguin search Optimisation Algorithm (PeSOA), a new metaheuristic algorithm which is inspired by the foraging behaviours of penguins. A population of penguins located in the solution space of the given search and optimisation problem is divided into groups and tasked with finding optimal solutions. The penguins of a group perform simultaneous dives and work as a team to collaboratively feed on fish the energy content of which corresponds to the fitness of candidate solutions. Fish stocks have higher fitness and concentration near areas of solution optima and thus drive the search. Penguins can migrate to other places if their original habitat lacks food. We identify two forms of penguin communication both intra-group and inter-group which are useful in designing intensification and diversification strategies. An efficient intensification strategy allows fast convergence to a local optimum, whereas an effective diversification strategy avoids cyclic behaviour around local optima and explores more effectively the space of potential solutions. The proposed PeSOA algorithm has been validated on a well-known set of benchmark functions. Comparative performances with six other nature-inspired metaheuristics show that the PeSOA performs favourably in these tests. A run-time analysis shows that the performance obtained by the PeSOA is very stable at any time of the evolution horizon, making the PeSOA a viable approach for real world applications. |
| Tasks | |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.09895v3 |
| http://arxiv.org/pdf/1809.09895v3.pdf | |
| PWC | https://paperswithcode.com/paper/pesoa-penguins-search-optimisation-algorithm |
| Repo | |
| Framework | |
Complex energy landscapes in spiked-tensor and simple glassy models: ruggedness, arrangements of local minima and phase transitions
| Title | Complex energy landscapes in spiked-tensor and simple glassy models: ruggedness, arrangements of local minima and phase transitions |
| Authors | Valentina Ros, Gerard Ben Arous, Giulio Biroli, Chiara Cammarota |
| Abstract | We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges. Such energy landscapes arise in glass physics and inference. In particular we focus on random Gaussian functions, and on the spiked-tensor model and generalizations. We thoroughly analyze the statistical properties of the corresponding landscapes and characterize the associated geometrical phase transitions. In order to perform our study, we develop a framework based on the Kac-Rice method that allows to compute the complexity of the landscape, i.e. the logarithm of the typical number of stationary points and their Hessian. This approach generalizes the one used to compute rigorously the annealed complexity of mean-field glass models. We discuss its advantages with respect to previous frameworks, in particular the thermodynamical replica method which is shown to lead to partially incorrect predictions. |
| Tasks | |
| Published | 2018-04-08 |
| URL | http://arxiv.org/abs/1804.02686v2 |
| http://arxiv.org/pdf/1804.02686v2.pdf | |
| PWC | https://paperswithcode.com/paper/complex-energy-landscapes-in-spiked-tensor |
| Repo | |
| Framework | |
Plan-Recognition-Driven Attention Modeling for Visual Recognition
| Title | Plan-Recognition-Driven Attention Modeling for Visual Recognition |
| Authors | Yantian Zha, Yikang Li, Tianshu Yu, Subbarao Kambhampati, Baoxin Li |
| Abstract | Human visual recognition of activities or external agents involves an interplay between high-level plan recognition and low-level perception. Given that, a natural question to ask is: can low-level perception be improved by high-level plan recognition? We formulate the problem of leveraging recognized plans to generate better top-down attention maps \cite{gazzaniga2009,baluch2011} to improve the perception performance. We call these top-down attention maps specifically as plan-recognition-driven attention maps. To address this problem, we introduce the Pixel Dynamics Network. Pixel Dynamics Network serves as an observation model, which predicts next states of object points at each pixel location given observation of pixels and pixel-level action feature. This is like internally learning a pixel-level dynamics model. Pixel Dynamics Network is a kind of Convolutional Neural Network (ConvNet), with specially-designed architecture. Therefore, Pixel Dynamics Network could take the advantage of parallel computation of ConvNets, while learning the pixel-level dynamics model. We further prove the equivalence between Pixel Dynamics Network as an observation model, and the belief update in partially observable Markov decision process (POMDP) framework. We evaluate our Pixel Dynamics Network in event recognition tasks. We build an event recognition system, ER-PRN, which takes Pixel Dynamics Network as a subroutine, to recognize events based on observations augmented by plan-recognition-driven attention. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00301v1 |
| http://arxiv.org/pdf/1812.00301v1.pdf | |
| PWC | https://paperswithcode.com/paper/plan-recognition-driven-attention-modeling |
| Repo | |
| Framework | |
Analysis and development of a novel algorithm for the in-vehicle hand-usage of a smartphone
| Title | Analysis and development of a novel algorithm for the in-vehicle hand-usage of a smartphone |
| Authors | Simone Gelmini, Silvia Strada, Mara Tanelli, Sergio Savaresi, Vincenzo Biase |
| Abstract | Smartphone usage while driving is unanimously considered to be a really dangerous habit due to strong correlation with road accidents. In this paper, the problem of detecting whether the driver is using the phone during a trip is addressed. To do this, high-frequency data from the triaxial inertial measurement unit (IMU) integrated in almost all modern phone is processed without relying on external inputs so as to provide a self-contained approach. By resorting to a frequency-domain analysis, it is possible to extract from the raw signals the useful information needed to detect when the driver is using the phone, without being affected by the effects that vehicle motion has on the same signals. The selected features are used to train a Support Vector Machine (SVM) algorithm. The performance of the proposed approach are analyzed and tested on experimental data collected during mixed naturalistic driving scenarios, proving the effectiveness of the proposed approach. |
| Tasks | |
| Published | 2018-04-06 |
| URL | http://arxiv.org/abs/1804.02960v2 |
| http://arxiv.org/pdf/1804.02960v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-and-development-of-a-novel-algorithm |
| Repo | |
| Framework | |
Towards Automated Post-Earthquake Inspections with Deep Learning-based Condition-Aware Models
| Title | Towards Automated Post-Earthquake Inspections with Deep Learning-based Condition-Aware Models |
| Authors | Vedhus Hoskere, Yasutaka Narazaki, Tu A. Hoang, Billie F. Spencer Jr |
| Abstract | In the aftermath of an earthquake, rapid structural inspections are required to get citizens back in to their homes and offices in a safe and timely manner. These inspections gfare typically conducted by municipal authorities through structural engineer volunteers. As manual inspec-tions can be time consuming, laborious and dangerous, research has been underway to develop methods to help speed up and increase the automation of the entire process. Researchers typi-cally envisage the use of unmanned aerial vehicles (UAV) for data acquisition and computer vision for data processing to extract actionable information. In this work we propose a new framework to generate vision-based condition-aware models that can serve as the basis for speeding up or automating higher level inspection decisions. The condition-aware models are generated by projecting the inference of trained deep-learning models on a set of images of a structure onto a 3D mesh model generated through multi-view stereo from the same image set. Deep fully convolutional residual networks are used for semantic segmentation of images of buildings to provide (i) damage information such as cracks and spalling (ii) contextual infor-mation such as the presence of a building and visually identifiable components like windows and doors. The proposed methodology was implemented on a damaged building that was sur-veyed by the authors after the Central Mexico Earthquake in September 2017 and qualitative-ly evaluated. Results demonstrate the promise of the proposed method towards the ultimate goal of rapid and automated post-earthquake inspections. |
| Tasks | Semantic Segmentation |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.09195v1 |
| http://arxiv.org/pdf/1809.09195v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automated-post-earthquake-inspections |
| Repo | |
| Framework | |
Channel Estimation for Visible Light Communications Using Neural Networks
| Title | Channel Estimation for Visible Light Communications Using Neural Networks |
| Authors | Anil Yesilkaya, Onur Karatalay, Arif Selcuk Ogrenci, Erdal Panayirci |
| Abstract | Visible light communications (VLC) is an emerging field in technology and research. Estimating the channel taps is a major requirement for designing reliable communication systems. Due to the nonlinear characteristics of the VLC channel those parameters cannot be derived easily. They can be calculated by means of software simulation. In this work, a novel methodology is proposed for the prediction of channel parameters using neural networks. Measurements conducted in a controlled experimental setup are used to train neural networks for channel tap prediction. Our experiment results indicate that neural networks can be effectively trained to predict channel taps under different environmental conditions. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08060v1 |
| http://arxiv.org/pdf/1805.08060v1.pdf | |
| PWC | https://paperswithcode.com/paper/channel-estimation-for-visible-light |
| Repo | |
| Framework | |
Learning-based Natural Geometric Matching with Homography Prior
| Title | Learning-based Natural Geometric Matching with Homography Prior |
| Authors | Yifang Xu, Tianli Liao, Jing Chen |
| Abstract | Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while we argue the importance of naturalness issue simultaneously. To deal with this, firstly, Pearson correlation is applied to handle large intra-class variations of features in feature matching stage. Then, we parametrize homography transformation with 9 parameters in full connected layer of our network, to better characterize large viewpoint variations compared with affine transformation. Furthermore, a novel loss function with Gaussian weights guarantees the model accuracy and efficiency in training procedure. Finally, we provide two choices for different purposes in geometric matching. When compositing homography with affine transformation, the alignment accuracy improves and all lines are preserved, which results in a more natural transformed image. When compositing homography with non-rigid thin-plate-spline transformation, the alignment accuracy further improves. Experimental results on Proposal Flow dataset show that our method outperforms state-of-the-art methods, both in terms of alignment accuracy and naturalness. |
| Tasks | |
| Published | 2018-07-13 |
| URL | http://arxiv.org/abs/1807.05119v1 |
| http://arxiv.org/pdf/1807.05119v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-natural-geometric-matching |
| Repo | |
| Framework | |
EEG Classification based on Image Configuration in Social Anxiety Disorder
| Title | EEG Classification based on Image Configuration in Social Anxiety Disorder |
| Authors | Lubna Shibly Mokatren, Rashid Ansari, Ahmet Enis Cetin, Alex D. Leow, Olusola Ajilore, Heide Klumpp, Fatos T. Yarman Vural |
| Abstract | The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. Performance of these two models is examined for analyzing 34 EEG data channels each consisting of five frequency bands and further decomposed with a filter bank. The data are collected from 64 subjects consisting of healthy controls and patients with SAD. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy $6$–$7%$ higher for model 2 for each machine learning algorithm we investigated. Convolutional Neural Networks (CNN) were found to provide much better performance than SVM and kNNs. |
| Tasks | EEG |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.02865v1 |
| http://arxiv.org/pdf/1812.02865v1.pdf | |
| PWC | https://paperswithcode.com/paper/eeg-classification-based-on-image |
| Repo | |
| Framework | |
The Evolution of Popularity and Images of Characters in Marvel Cinematic Universe Fanfictions
| Title | The Evolution of Popularity and Images of Characters in Marvel Cinematic Universe Fanfictions |
| Authors | Fan Bu |
| Abstract | This analysis proposes a new topic model to study the yearly trends in Marvel Cinematic Universe fanfictions on three levels: character popularity, character images/topics, and vocabulary pattern of topics. It is found that character appearances in fanfictions have become more diverse over the years thanks to constant introduction of new characters in feature films, and in the case of Captain America, multi-dimensional character development is well-received by the fanfiction world. |
| Tasks | |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.03774v1 |
| http://arxiv.org/pdf/1805.03774v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-evolution-of-popularity-and-images-of |
| Repo | |
| Framework | |
t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification
| Title | t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification |
| Authors | Tomi Kinnunen, Kong Aik Lee, Hector Delgado, Nicholas Evans, Massimiliano Todisco, Md Sahidullah, Junichi Yamagishi, Douglas A. Reynolds |
| Abstract | The ASVspoof challenge series was born to spearhead research in anti-spoofing for automatic speaker verification (ASV). The two challenge editions in 2015 and 2017 involved the assessment of spoofing countermeasures (CMs) in isolation from ASV using an equal error rate (EER) metric. While a strategic approach to assessment at the time, it has certain shortcomings. First, the CM EER is not necessarily a reliable predictor of performance when ASV and CMs are combined. Second, the EER operating point is ill-suited to user authentication applications, e.g. telephone banking, characterised by a high target user prior but a low spoofing attack prior. We aim to migrate from CM- to ASV-centric assessment with the aid of a new tandem detection cost function (t-DCF) metric. It extends the conventional DCF used in ASV research to scenarios involving spoofing attacks. The t-DCF metric has 6 parameters: (i) false alarm and miss costs for both systems, and (ii) prior probabilities of target and spoof trials (with an implied third, nontarget prior). The study is intended to serve as a self-contained, tutorial-like presentation. We analyse with the t-DCF a selection of top-performing CM submissions to the 2015 and 2017 editions of ASVspoof, with a focus on the spoofing attack prior. Whereas there is little to choose between countermeasure systems for lower priors, system rankings derived with the EER and t-DCF show differences for higher priors. We observe some ranking changes. Findings support the adoption of the DCF-based metric into the roadmap for future ASVspoof challenges, and possibly for other biometric anti-spoofing evaluations. |
| Tasks | Speaker Verification |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09618v2 |
| http://arxiv.org/pdf/1804.09618v2.pdf | |
| PWC | https://paperswithcode.com/paper/t-dcf-a-detection-cost-function-for-the |
| Repo | |
| Framework | |
OrthoNet: Multilayer Network Data Clustering
| Title | OrthoNet: Multilayer Network Data Clustering |
| Authors | Mireille El Gheche, Giovanni Chierchia, Pascal Frossard |
| Abstract | Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very common task in machine learning and data mining. Network data comes with some information about the network edges. In some cases, this network information can even be given with multiple views or multiple layers, each one representing a different type of relationship between the network nodes. Increasingly often, network nodes also carry a feature vector. We propose in this paper to extend the node clustering problem, that commonly considers only the network information, to a problem where both the network information and the node features are considered together for learning a clustering-friendly representation of the feature space. Specifically, we design a generic two-step algorithm for multilayer network data clustering. The first step aggregates the different layers of network information into a graph representation given by the geometric mean of the network Laplacian matrices. The second step uses a neural net to learn a feature embedding that is consistent with the structure given by the network layers. We propose a novel algorithm for efficiently training the neural net via stochastic gradient descent, which encourages the neural net outputs to span the leading eigenvectors of the aggregated Laplacian matrix, in order to capture the pairwise interactions on the network, and provide a clustering-friendly representation of the feature space. We demonstrate with an extensive set of experiments on synthetic and real datasets that our method leads to a significant improvement w.r.t. state-of-the-art multilayer graph clustering algorithms, as it judiciously combines nodes features and network information in the node embedding algorithms. |
| Tasks | Graph Clustering |
| Published | 2018-11-02 |
| URL | https://arxiv.org/abs/1811.00821v5 |
| https://arxiv.org/pdf/1811.00821v5.pdf | |
| PWC | https://paperswithcode.com/paper/multilayer-graph-signal-clustering |
| Repo | |
| Framework | |
