Paper Group ANR 176
Weighted Abstract Dialectical Frameworks: Extended and Revised Report. Towards Neural Co-Processors for the Brain: Combining Decoding and Encoding in Brain-Computer Interfaces. Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fall with Grace. Language Identification in Code-Mixed Data using Multichannel Neural Network …
Weighted Abstract Dialectical Frameworks: Extended and Revised Report
Title | Weighted Abstract Dialectical Frameworks: Extended and Revised Report |
Authors | Gerhard Brewka, Jörg Pührer, Hannes Strass, Johannes P. Wallner, Stefan Woltran |
Abstract | Abstract Dialectical Frameworks (ADFs) generalize Dung’s argumentation frameworks allowing various relationships among arguments to be expressed in a systematic way. We further generalize ADFs so as to accommodate arbitrary acceptance degrees for the arguments. This makes ADFs applicable in domains where both the initial status of arguments and their relationship are only insufficiently specified by Boolean functions. We define all standard ADF semantics for the weighted case, including grounded, preferred and stable semantics. We illustrate our approach using acceptance degrees from the unit interval and show how other valuation structures can be integrated. In each case it is sufficient to specify how the generalized acceptance conditions are represented by formulas, and to specify the information ordering underlying the characteristic ADF operator. We also present complexity results for problems related to weighted ADFs. |
Tasks | |
Published | 2018-06-20 |
URL | http://arxiv.org/abs/1806.07717v2 |
http://arxiv.org/pdf/1806.07717v2.pdf | |
PWC | https://paperswithcode.com/paper/weighted-abstract-dialectical-frameworks |
Repo | |
Framework | |
Towards Neural Co-Processors for the Brain: Combining Decoding and Encoding in Brain-Computer Interfaces
Title | Towards Neural Co-Processors for the Brain: Combining Decoding and Encoding in Brain-Computer Interfaces |
Authors | Rajesh P. N. Rao |
Abstract | The field of brain-computer interfaces is poised to advance from the traditional goal of controlling prosthetic devices using brain signals to combining neural decoding and encoding within a single neuroprosthetic device. Such a device acts as a “co-processor” for the brain, with applications ranging from inducing Hebbian plasticity for rehabilitation after brain injury to reanimating paralyzed limbs and enhancing memory. We review recent progress in simultaneous decoding and encoding for closed-loop control and plasticity induction. To address the challenge of multi-channel decoding and encoding, we introduce a unifying framework for developing brain co-processors based on artificial neural networks and deep learning. These “neural co-processors” can be used to jointly optimize cost functions with the nervous system to achieve desired behaviors ranging from targeted neuro-rehabilitation to augmentation of brain function. |
Tasks | |
Published | 2018-11-28 |
URL | http://arxiv.org/abs/1811.11876v2 |
http://arxiv.org/pdf/1811.11876v2.pdf | |
PWC | https://paperswithcode.com/paper/towards-neural-co-processors-for-the-brain |
Repo | |
Framework | |
Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fall with Grace
Title | Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fall with Grace |
Authors | Steve Heim, Alexander Spröwitz |
Abstract | Despite impressive results using reinforcement learning to solve complex problems from scratch, in robotics this has still been largely limited to model-based learning with very informative reward functions. One of the major challenges is that the reward landscape often has large patches with no gradient, making it difficult to sample gradients effectively. We show here that the robot state-initialization can have a more important effect on the reward landscape than is generally expected. In particular, we show the counter-intuitive benefit of including initializations that are unviable, in other words initializing in states that are doomed to fail. |
Tasks | |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06569v1 |
http://arxiv.org/pdf/1806.06569v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-from-outside-the-viability-kernel |
Repo | |
Framework | |
Language Identification in Code-Mixed Data using Multichannel Neural Networks and Context Capture
Title | Language Identification in Code-Mixed Data using Multichannel Neural Networks and Context Capture |
Authors | Soumil Mandal, Anil Kumar Singh |
Abstract | An accurate language identification tool is an absolute necessity for building complex NLP systems to be used on code-mixed data. Lot of work has been recently done on the same, but there’s still room for improvement. Inspired from the recent advancements in neural network architectures for computer vision tasks, we have implemented multichannel neural networks combining CNN and LSTM for word level language identification of code-mixed data. Combining this with a Bi-LSTM-CRF context capture module, accuracies of 93.28% and 93.32% is achieved on our two testing sets. |
Tasks | Language Identification |
Published | 2018-08-21 |
URL | http://arxiv.org/abs/1808.07118v1 |
http://arxiv.org/pdf/1808.07118v1.pdf | |
PWC | https://paperswithcode.com/paper/language-identification-in-code-mixed-data |
Repo | |
Framework | |
Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection
Title | Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection |
Authors | Tae Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik |
Abstract | This short paper describes our ongoing research on Greenhouse - a zero-positive machine learning system for time-series anomaly detection. |
Tasks | Anomaly Detection, Time Series |
Published | 2018-01-09 |
URL | http://arxiv.org/abs/1801.03168v3 |
http://arxiv.org/pdf/1801.03168v3.pdf | |
PWC | https://paperswithcode.com/paper/greenhouse-a-zero-positive-machine-learning |
Repo | |
Framework | |
3D Human Body Reconstruction from a Single Image via Volumetric Regression
Title | 3D Human Body Reconstruction from a Single Image via Volumetric Regression |
Authors | Aaron S. Jackson, Chris Manafas, Georgios Tzimiropoulos |
Abstract | This paper proposes the use of an end-to-end Convolutional Neural Network for direct reconstruction of the 3D geometry of humans via volumetric regression. The proposed method does not require the fitting of a shape model and can be trained to work from a variety of input types, whether it be landmarks, images or segmentation masks. Additionally, non-visible parts, either self-occluded or otherwise, are still reconstructed, which is not the case with depth map regression. We present results that show that our method can handle both pose variation and detailed reconstruction given appropriate datasets for training. |
Tasks | |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.03770v1 |
http://arxiv.org/pdf/1809.03770v1.pdf | |
PWC | https://paperswithcode.com/paper/3d-human-body-reconstruction-from-a-single |
Repo | |
Framework | |
Fusion++: Volumetric Object-Level SLAM
Title | Fusion++: Volumetric Object-Level SLAM |
Authors | John McCormac, Ronald Clark, Michael Bloesch, Andrew J. Davison, Stefan Leutenegger |
Abstract | We propose an online object-level SLAM system which builds a persistent and accurate 3D graph map of arbitrary reconstructed objects. As an RGB-D camera browses a cluttered indoor scene, Mask-RCNN instance segmentations are used to initialise compact per-object Truncated Signed Distance Function (TSDF) reconstructions with object size-dependent resolutions and a novel 3D foreground mask. Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation. Objects are incrementally refined via depth fusion, and are used for tracking, relocalisation and loop closure detection. Loop closures cause adjustments in the relative pose estimates of object instances, but no intra-object warping. Each object also carries semantic information which is refined over time and an existence probability to account for spurious instance predictions. We demonstrate our approach on a hand-held RGB-D sequence from a cluttered office scene with a large number and variety of object instances, highlighting how the system closes loops and makes good use of existing objects on repeated loops. We quantitatively evaluate the trajectory error of our system against a baseline approach on the RGB-D SLAM benchmark, and qualitatively compare reconstruction quality of discovered objects on the YCB video dataset. Performance evaluation shows our approach is highly memory efficient and runs online at 4-8Hz (excluding relocalisation) despite not being optimised at the software level. |
Tasks | Loop Closure Detection |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08378v2 |
http://arxiv.org/pdf/1808.08378v2.pdf | |
PWC | https://paperswithcode.com/paper/fusion-volumetric-object-level-slam |
Repo | |
Framework | |
A Predictive Model for Music Based on Learned Interval Representations
Title | A Predictive Model for Music Based on Learned Interval Representations |
Authors | Stefan Lattner, Maarten Grachten, Gerhard Widmer |
Abstract | Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly “absolute pitch perception”. Therefore, they fail to generalize over musical concepts which are commonly perceived in terms of relative distances between pitches (e.g., melodies, scale types, modes, cadences, or chord types). Second, they fall short of capturing the concepts of repetition and musical form. In this paper we introduce the recurrent gated autoencoder (RGAE), a recurrent neural network which learns and operates on interval representations of musical sequences. The relative pitch modeling increases generalization and reduces sparsity in the input data. Furthermore, it can learn sequences of copy-and-shift operations (i.e. chromatically transposed copies of musical fragments)—a promising capability for learning musical repetition structure. We show that the RGAE improves the state of the art for general connectionist sequence models in learning to predict monophonic melodies, and that ensembles of relative and absolute music processing models improve the results appreciably. Furthermore, we show that the relative pitch processing of the RGAE naturally facilitates the learning and the generation of sequences of copy-and-shift operations, wherefore the RGAE greatly outperforms a common absolute pitch recurrent neural network on this task. |
Tasks | |
Published | 2018-06-22 |
URL | http://arxiv.org/abs/1806.08686v1 |
http://arxiv.org/pdf/1806.08686v1.pdf | |
PWC | https://paperswithcode.com/paper/a-predictive-model-for-music-based-on-learned |
Repo | |
Framework | |
The New Modality: Emoji Challenges in Prediction, Anticipation, and Retrieval
Title | The New Modality: Emoji Challenges in Prediction, Anticipation, and Retrieval |
Authors | Spencer Cappallo, Stacey Svetlichnaya, Pierre Garrigues, Thomas Mensink, Cees G. M. Snoek |
Abstract | Over the past decade, emoji have emerged as a new and widespread form of digital communication, spanning diverse social networks and spoken languages. We propose to treat these ideograms as a new modality in their own right, distinct in their semantic structure from both the text in which they are often embedded as well as the images which they resemble. As a new modality, emoji present rich novel possibilities for representation and interaction. In this paper, we explore the challenges that arise naturally from considering the emoji modality through the lens of multimedia research. Specifically, the ways in which emoji can be related to other common modalities such as text and images. To do so, we first present a large scale dataset of real-world emoji usage collected from Twitter. This dataset contains examples of both text-emoji and image-emoji relationships. We present baseline results on the challenge of predicting emoji from both text and images, using state-of-the-art neural networks. Further, we offer a first consideration into the problem of how to account for new, unseen emoji - a relevant issue as the emoji vocabulary continues to expand on a yearly basis. Finally, we present results for multimedia retrieval using emoji as queries. |
Tasks | |
Published | 2018-01-30 |
URL | http://arxiv.org/abs/1801.10253v2 |
http://arxiv.org/pdf/1801.10253v2.pdf | |
PWC | https://paperswithcode.com/paper/the-new-modality-emoji-challenges-in |
Repo | |
Framework | |
Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
Title | Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs |
Authors | Jerry Li |
Abstract | We present a framework for translating unlabeled images from one domain into analog images in another domain. We employ a progressively growing skip-connected encoder-generator structure and train it with a GAN loss for realistic output, a cycle consistency loss for maintaining same-domain translation identity, and a semantic consistency loss that encourages the network to keep the input semantic features in the output. We apply our framework on the task of translating face images, and show that it is capable of learning semantic mappings for face images with no supervised one-to-one image mapping. |
Tasks | |
Published | 2018-08-26 |
URL | http://arxiv.org/abs/1809.00946v1 |
http://arxiv.org/pdf/1809.00946v1.pdf | |
PWC | https://paperswithcode.com/paper/twin-gan-unpaired-cross-domain-image |
Repo | |
Framework | |
A Theoretical Framework of Approximation Error Analysis of Evolutionary Algorithms
Title | A Theoretical Framework of Approximation Error Analysis of Evolutionary Algorithms |
Authors | Jun He, Yu Chen, Yuren Zhou |
Abstract | In the empirical study of evolutionary algorithms, the solution quality is evaluated by either the fitness value or approximation error. The latter measures the fitness difference between an approximation solution and the optimal solution. Since the approximation error analysis is more convenient than the direct estimation of the fitness value, this paper focuses on approximation error analysis. However, it is straightforward to extend all related results from the approximation error to the fitness value. Although the evaluation of solution quality plays an essential role in practice, few rigorous analyses have been conducted on this topic. This paper aims at establishing a novel theoretical framework of approximation error analysis of evolutionary algorithms for discrete optimization. This framework is divided into two parts. The first part is about exact expressions of the approximation error. Two methods, Jordan form and Schur’s triangularization, are presented to obtain an exact expression. The second part is about upper bounds on approximation error. Two methods, convergence rate and auxiliary matrix iteration, are proposed to estimate the upper bound. The applicability of this framework is demonstrated through several examples. |
Tasks | |
Published | 2018-10-26 |
URL | http://arxiv.org/abs/1810.11532v1 |
http://arxiv.org/pdf/1810.11532v1.pdf | |
PWC | https://paperswithcode.com/paper/a-theoretical-framework-of-approximation |
Repo | |
Framework | |
Bayesian Reinforcement Learning in Factored POMDPs
Title | Bayesian Reinforcement Learning in Factored POMDPs |
Authors | Sammie Katt, Frans Oliehoek, Christopher Amato |
Abstract | Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of solving the underlying problem near-optimally. Our method is able to learn efficiently given a known factorization or also learn the factorization and the model parameters at the same time. We demonstrate that this approach is able to outperform current methods and tackle problems that were previously infeasible. |
Tasks | |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.05612v1 |
http://arxiv.org/pdf/1811.05612v1.pdf | |
PWC | https://paperswithcode.com/paper/bayesian-reinforcement-learning-in-factored |
Repo | |
Framework | |
Interpreting Layered Neural Networks via Hierarchical Modular Representation
Title | Interpreting Layered Neural Networks via Hierarchical Modular Representation |
Authors | Chihiro Watanabe |
Abstract | Interpreting the prediction mechanism of complex models is currently one of the most important tasks in the machine learning field, especially with layered neural networks, which have achieved high predictive performance with various practical data sets. To reveal the global structure of a trained neural network in an interpretable way, a series of clustering methods have been proposed, which decompose the units into clusters according to the similarity of their inference roles. The main problems in these studies were that (1) we have no prior knowledge about the optimal resolution for the decomposition, or the appropriate number of clusters, and (2) there was no method with which to acquire knowledge about whether the outputs of each cluster have a positive or negative correlation with the input and output dimension values. In this paper, to solve these problems, we propose a method for obtaining a hierarchical modular representation of a layered neural network. The application of a hierarchical clustering method to a trained network reveals a tree-structured relationship among hidden layer units, based on their feature vectors defined by their correlation with the input and output dimension values. |
Tasks | |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01588v1 |
http://arxiv.org/pdf/1810.01588v1.pdf | |
PWC | https://paperswithcode.com/paper/interpreting-layered-neural-networks-via |
Repo | |
Framework | |
Precision and Recall for Range-Based Anomaly Detection
Title | Precision and Recall for Range-Based Anomaly Detection |
Authors | Tae Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik |
Abstract | Classical anomaly detection is principally concerned with point-based anomalies, anomalies that occur at a single data point. In this paper, we present a new mathematical model to express range-based anomalies, anomalies that occur over a range (or period) of time. |
Tasks | Anomaly Detection |
Published | 2018-01-09 |
URL | http://arxiv.org/abs/1801.03175v3 |
http://arxiv.org/pdf/1801.03175v3.pdf | |
PWC | https://paperswithcode.com/paper/precision-and-recall-for-range-based-anomaly |
Repo | |
Framework | |
Sequence to Sequence Learning for Query Expansion
Title | Sequence to Sequence Learning for Query Expansion |
Authors | Salah Zaiem, Fatiha Sadat |
Abstract | Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering’s. We tried to fill this gap in the literature with a custom Query Expansion engine trained and tested on open datasets. Starting from open datasets, we built a Query Expansion training set using sentence-embeddings-based Keyword Extraction. We therefore assessed the ability of the Sequence to Sequence neural networks to capture expanding relations in the words embeddings’ space. |
Tasks | Information Retrieval, Keyword Extraction, Sentence Embeddings |
Published | 2018-12-25 |
URL | http://arxiv.org/abs/1812.10119v1 |
http://arxiv.org/pdf/1812.10119v1.pdf | |
PWC | https://paperswithcode.com/paper/sequence-to-sequence-learning-for-query |
Repo | |
Framework | |