Paper Group ANR 1041
Modeling the Complexity and Descriptive Adequacy of Construction Grammars. Instruction-Level Design of Local Optimisers using Push GP. Accelerating Training in Pommerman with Imitation and Reinforcement Learning. Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation. 3D CNN with Localized Residual Connection …
Modeling the Complexity and Descriptive Adequacy of Construction Grammars
| Title | Modeling the Complexity and Descriptive Adequacy of Construction Grammars |
| Authors | Jonathan Dunn |
| Abstract | This paper uses the Minimum Description Length paradigm to model the complexity of CxGs (operationalized as the encoding size of a grammar) alongside their descriptive adequacy (operationalized as the encoding size of a corpus given a grammar). These two quantities are combined to measure the quality of potential CxGs against unannotated corpora, supporting discovery-device CxGs for English, Spanish, French, German, and Italian. The results show (i) that these grammars provide significant generalizations as measured using compression and (ii) that more complex CxGs with access to multiple levels of representation provide greater generalizations than single-representation CxGs. |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05588v1 |
| http://arxiv.org/pdf/1904.05588v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-the-complexity-and-descriptive-1 |
| Repo | |
| Framework | |
Instruction-Level Design of Local Optimisers using Push GP
| Title | Instruction-Level Design of Local Optimisers using Push GP |
| Authors | Michael Lones |
| Abstract | This work uses genetic programming to explore the design space of local optimisation algorithms. Optimisers are expressed in the Push programming language, a stack-based language with a wide range of typed primitive instructions. The evolutionary framework provides the evolving optimisers with an outer loop and information about whether a solution has improved, but otherwise they are relatively unconstrained in how they explore optimisation landscapes. To test the utility of this approach, optimisers were evolved on four different types of continuous landscape, and the search behaviours of the evolved optimisers analysed. By making use of mathematical functions such as tangents and logarithms to explore different neighbourhoods, and also by learning features of the landscapes, it was observed that the evolved optimisers were often able to reach the optima using relatively short paths. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10245v1 |
| https://arxiv.org/pdf/1905.10245v1.pdf | |
| PWC | https://paperswithcode.com/paper/instruction-level-design-of-local-optimisers |
| Repo | |
| Framework | |
Accelerating Training in Pommerman with Imitation and Reinforcement Learning
| Title | Accelerating Training in Pommerman with Imitation and Reinforcement Learning |
| Authors | Hardik Meisheri, Omkar Shelke, Richa Verma, Harshad Khadilkar |
| Abstract | The Pommerman simulation was recently developed to mimic the classic Japanese game Bomberman, and focuses on competitive gameplay in a multi-agent setting. We focus on the 2$\times$2 team version of Pommerman, developed for a competition at NeurIPS 2018. Our methodology involves training an agent initially through imitation learning on a noisy expert policy, followed by a proximal-policy optimization (PPO) reinforcement learning algorithm. The basic PPO approach is modified for stable transition from the imitation learning phase through reward shaping, action filters based on heuristics, and curriculum learning. The proposed methodology is able to beat heuristic and pure reinforcement learning baselines with a combined 100,000 training games, significantly faster than other non-tree-search methods in literature. We present results against multiple agents provided by the developers of the simulation, including some that we have enhanced. We include a sensitivity analysis over different parameters, and highlight undesirable effects of some strategies that initially appear promising. Since Pommerman is a complex multi-agent competitive environment, the strategies developed here provide insights into several real-world problems with characteristics such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards. |
| Tasks | Imitation Learning |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04947v2 |
| https://arxiv.org/pdf/1911.04947v2.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-training-in-pommerman-with |
| Repo | |
| Framework | |
Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation
| Title | Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation |
| Authors | Mihai Marian Puscas, Dan Xu, Andrea Pilzer, Nicu Sebe |
| Abstract | Inspired by the success of adversarial learning, we propose a new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled with a structured Conditional Random Field (CRF) model. The two GANs aim at generating distinct and complementary disparity maps and at improving the generation quality via exploiting the adversarial learning strategy. The deep CRF coupling model is proposed to fuse the generative and discriminative outputs from the dual GAN nets. As such, the model implicitly constructs mutual constraints on the two network branches and between the generator and discriminator. This facilitates the optimization of the whole network for better disparity generation. Extensive experiments on the KITTI, Cityscapes, and Make3D datasets clearly demonstrate the effectiveness of the proposed approach and show superior performance compared to state of the art methods. The code and models are available at https://github.com/mihaipuscas/ 3dv—coupled-crf-disparity. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05794v1 |
| https://arxiv.org/pdf/1908.05794v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-coupled-generative-adversarial |
| Repo | |
| Framework | |
3D CNN with Localized Residual Connections for Hyperspectral Image Classification
| Title | 3D CNN with Localized Residual Connections for Hyperspectral Image Classification |
| Authors | Shivangi Dwivedi, Murari Mandal, Shekhar Yadav, Santosh Kumar Vipparthi |
| Abstract | In this paper we propose a novel 3D CNN network with localized residual connections for hyperspectral image classification. Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a model which incorporates residual features from multiple stages in the network. The proposed architecture processes individual spatiospectral feature rich cubes from hyperspectral images through 3D convolutional layers. The residual connections result in improved performance due to assimilation of both low-level and high-level features. We conduct experiments over Pavia University and Pavia Center dataset for performance analysis. We compare our method with two recent state-of-the-art methods for hyperspectral image classification method. The proposed network outperforms the existing approaches by a good margin. |
| Tasks | Hyperspectral Image Classification, Image Classification |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03000v1 |
| https://arxiv.org/pdf/1912.03000v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-cnn-with-localized-residual-connections |
| Repo | |
| Framework | |
Hydrocephalus verification on brain magnetic resonance images with deep convolutional neural networks and “transfer learning” technique
| Title | Hydrocephalus verification on brain magnetic resonance images with deep convolutional neural networks and “transfer learning” technique |
| Authors | Alexey Demyanchuk, Ekaterina Pushkina, Nikolay Russkikh, Dmitry Shtokalo, Sergey Mishinov |
| Abstract | The hydrocephalus can be either an independent disease or a concomitant symptom of a number of pathologies, therefore representing an urgent issue in the present-day clinical practice. Deep Learning is an evolving technology and the part of a broader field of Machine Learning. Deep learning is currently actively researched in the field of radiology. The aim of this study was to evaluate deep learning applicability to the diagnostics of hydrocephalus with the use of MRI images. We retrospectively collected, annotated, and preprocessed the brain MRI data of 200 patients with and without radiological signs of hydrocephalus. We applied a state-of-the-art deep convolutional neural network in conjunction with transfer learning method to train a hydrocephalus classifier model. Using deep convolutional neural networks, we achieved a high quality of machine learning model. Accuracy, sensitivity, and specificity of hydrocephalus signs identification was 97%, 98%, and 96% respectively. In this study, we demonstrated the capacity of deep neural networks to identify hydrocephalus syndrome using brain MRI images. Applying transfer learning technique, the high quality of classification was achieved although trained on rather limited data. |
| Tasks | Transfer Learning |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10473v1 |
| https://arxiv.org/pdf/1909.10473v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910473 |
| Repo | |
| Framework | |
A Bayesian Choice Model for Eliminating Feedback Loops
| Title | A Bayesian Choice Model for Eliminating Feedback Loops |
| Authors | Gökhan Çapan, Ilker Gündoğdu, Ali Caner Türkmen, Çağrı Sofuoğlu, Ali Taylan Cemgil |
| Abstract | Self-reinforcing feedback loops in personalization systems are typically caused by users choosing from a limited set of alternatives presented systematically based on previous choices. We propose a Bayesian choice model built on Luce axioms that explicitly accounts for users’ limited exposure to alternatives. Our model is fair—it does not impose negative bias towards unpresented alternatives, and practical—preference estimates are accurately inferred upon observing a small number of interactions. It also allows efficient sampling, leading to a straightforward online presentation mechanism based on Thompson sampling. Our approach achieves low regret in learning to present upon exploration of only a small fraction of possible presentations. The proposed structure can be reused as a building block in interactive systems, e.g., recommender systems, free of feedback loops. |
| Tasks | Recommendation Systems |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05640v2 |
| https://arxiv.org/pdf/1908.05640v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-choice-model-for-eliminating |
| Repo | |
| Framework | |
GAIT: A Geometric Approach to Information Theory
| Title | GAIT: A Geometric Approach to Information Theory |
| Authors | Jose Gallego, Ankit Vani, Max Schwarzer, Simon Lacoste-Julien |
| Abstract | We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities between them. This concept was originally introduced in theoretical ecology to study the diversity of ecosystems. Based on this notion of entropy, we introduce geometry-aware counterparts for several concepts and theorems in information theory. Notably, our proposed divergence exhibits performance on par with state-of-the-art methods based on the Wasserstein distance, but enjoys a closed-form expression that can be computed efficiently. We demonstrate the versatility of our method via experiments on a broad range of domains: training generative models, computing image barycenters, approximating empirical measures and counting modes. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08325v2 |
| https://arxiv.org/pdf/1906.08325v2.pdf | |
| PWC | https://paperswithcode.com/paper/gear-geometry-aware-renyi-information |
| Repo | |
| Framework | |
Invariance and identifiability issues for word embeddings
| Title | Invariance and identifiability issues for word embeddings |
| Authors | Rachel Carrington, Karthik Bharath, Simon Preston |
| Abstract | Word embeddings are commonly obtained as optimizers of a criterion function $f$ of a text corpus, but assessed on word-task performance using a different evaluation function $g$ of the test data. We contend that a possible source of disparity in performance on tasks is the incompatibility between classes of transformations that leave $f$ and $g$ invariant. In particular, word embeddings defined by $f$ are not unique; they are defined only up to a class of transformations to which $f$ is invariant, and this class is larger than the class to which $g$ is invariant. One implication of this is that the apparent superiority of one word embedding over another, as measured by word task performance, may largely be a consequence of the arbitrary elements selected from the respective solution sets. We provide a formal treatment of the above identifiability issue, present some numerical examples, and discuss possible resolutions. |
| Tasks | Word Embeddings |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02656v1 |
| https://arxiv.org/pdf/1911.02656v1.pdf | |
| PWC | https://paperswithcode.com/paper/invariance-and-identifiability-issues-for |
| Repo | |
| Framework | |
Direct Visual-Inertial Odometry with Semi-Dense Mapping
| Title | Direct Visual-Inertial Odometry with Semi-Dense Mapping |
| Authors | Wenju Xu, Dongkyu Choi, Guanghui Wang |
| Abstract | The paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent advances in direct dense tracking and Inertial Measurement Unit (IMU) pre-integration, and a factor graph optimization is adapted to estimate the pose of the camera and rebuild a semi-dense map. Two sliding windows are maintained in the proposed approach. The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking. In the second one, measurements from the IMU pre-integration and dense visual tracking are fused probabilistically using a tightly-coupled, optimization-based sensor fusion framework. As a result, the IMU pre-integration provides additional constraints to suppress the scale drift induced by the visual odometry. Evaluations on real-world benchmark datasets show that the proposed method achieves competitive results in indoor scenes. |
| Tasks | Sensor Fusion, Visual Odometry, Visual Tracking |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02106v1 |
| https://arxiv.org/pdf/1910.02106v1.pdf | |
| PWC | https://paperswithcode.com/paper/direct-visual-inertial-odometry-with-semi |
| Repo | |
| Framework | |
SLAM Endoscopy enhanced by adversarial depth prediction
| Title | SLAM Endoscopy enhanced by adversarial depth prediction |
| Authors | Richard J. Chen, Taylor L. Bobrow, Thomas Athey, Faisal Mahmood, Nicholas J. Durr |
| Abstract | Medical endoscopy remains a challenging application for simultaneous localization and mapping (SLAM) due to the sparsity of image features and size constraints that prevent direct depth-sensing. We present a SLAM approach that incorporates depth predictions made by an adversarially-trained convolutional neural network (CNN) applied to monocular endoscopy images. The depth network is trained with synthetic images of a simple colon model, and then fine-tuned with domain-randomized, photorealistic images rendered from computed tomography measurements of human colons. Each image is paired with an error-free depth map for supervised adversarial learning. Monocular RGB images are then fused with corresponding depth predictions, enabling dense reconstruction and mosaicing as an endoscope is advanced through the gastrointestinal tract. Our preliminary results demonstrate that incorporating monocular depth estimation into a SLAM architecture can enable dense reconstruction of endoscopic scenes. |
| Tasks | Depth Estimation, Monocular Depth Estimation, Simultaneous Localization and Mapping |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00283v1 |
| https://arxiv.org/pdf/1907.00283v1.pdf | |
| PWC | https://paperswithcode.com/paper/slam-endoscopy-enhanced-by-adversarial-depth |
| Repo | |
| Framework | |
Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI
| Title | Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI |
| Authors | Georgia Koppe, Hazem Toutounji, Peter Kirsch, Stefanie Lis, Daniel Durstewitz |
| Abstract | A major tenet in theoretical neuroscience is that cognitive and behavioral processes are ultimately implemented in terms of the neural system dynamics. Accordingly, a major aim for the analysis of neurophysiological measurements should lie in the identification of the computational dynamics underlying task processing. Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data. In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems analysis of the resulting set of equations, and can straightforwardly be transformed into an equivalent continuous-time dynamical system. The major contributions of this paper are the introduction of a new observation model suitable for functional magnetic resonance imaging (fMRI) coupled to the latent PLRNN, an efficient stepwise training procedure that forces the latent model to capture the ‘true’ underlying dynamics rather than just fitting (or predicting) the observations, and of an empirical measure based on the Kullback-Leibler divergence to evaluate from empirical time series how well this goal of approximating the underlying dynamics has been achieved. We validate and illustrate the power of our approach on simulated ‘ground-truth’ dynamical (benchmark) systems as well as on actual experimental fMRI time series, and demonstrate that the latent dynamics harbors task-related nonlinear structure that a linear dynamical model fails to capture. Given that fMRI is one of the most common techniques for measuring brain activity non-invasively in human subjects, this approach may provide a novel step toward analyzing aberrant (nonlinear) dynamics for clinical assessment or neuroscientific research. |
| Tasks | Time Series |
| Published | 2019-02-19 |
| URL | https://arxiv.org/abs/1902.07186v2 |
| https://arxiv.org/pdf/1902.07186v2.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-nonlinear-dynamical-systems-via |
| Repo | |
| Framework | |
Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning
| Title | Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning |
| Authors | Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, Guodong Zhou |
| Abstract | Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper, to simulating the steps of analyzing aspect sentiment in a document by human beings, we propose a new Hierarchical Reinforcement Learning (HRL) approach to DASC. This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC. First, a high-level policy is proposed to select aspect-relevant clauses and discard noisy clauses. Then, a low-level policy is proposed to select sentiment-relevant words and discard noisy words inside the selected clauses. Finally, a sentiment rating predictor is designed to provide reward signals to guide both clause and word selection. Experimental results demonstrate the impressive effectiveness of the proposed approach to DASC over the state-of-the-art baselines. |
| Tasks | Decision Making, Hierarchical Reinforcement Learning, Sentiment Analysis |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09260v1 |
| https://arxiv.org/pdf/1910.09260v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-like-decision-making-document-level |
| Repo | |
| Framework | |
Stochastic Submodular Probing with State-Dependent Costs
| Title | Stochastic Submodular Probing with State-Dependent Costs |
| Authors | Shaojie Tang |
| Abstract | In this paper, we study a new stochastic submodular maximization problem with state-dependent costs and rejections. The input of our problem is a budget constraint $B$, and a set of items whose states (i.e., the marginal contribution and the cost of an item) are drawn from a known probability distribution. The only way to know the realized state of an item is to probe the item. We allow rejections, i.e., after probing an item and knowing its actual state, we must decide immediately and irrevocably whether to add that item to our solution or not. Our objective is to maximize the objective function subject to a budget constraint on the total cost of the selected items. We present a constant approximate solution to this problem. We show that our solution is also applied to an online setting. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.01795v1 |
| https://arxiv.org/pdf/1909.01795v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-submodular-probing-with-state |
| Repo | |
| Framework | |
Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods
| Title | Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods |
| Authors | Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way |
| Abstract | Data selection has proven its merit for improving Neural Machine Translation (NMT), when applied to authentic data. But the benefit of using synthetic data in NMT training, produced by the popular back-translation technique, raises the question if data selection could also be useful for synthetic data? In this work we use Infrequent N-gram Recovery (INR) and Feature Decay Algorithms (FDA), two transductive data selection methods to obtain subsets of sentences from synthetic data. These methods ensure that selected sentences share n-grams with the test set so the NMT model can be adapted to translate it. Performing data selection on back-translated data creates new challenges as the source-side may contain noise originated by the model used in the back-translation. Hence, finding n-grams present in the test set become more difficult. Despite that, in our work we show that adapting a model with a selection of synthetic data is an useful approach. |
| Tasks | Machine Translation |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07808v1 |
| https://arxiv.org/pdf/1906.07808v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptation-of-machine-translation-models-with |
| Repo | |
| Framework | |
