January 28, 2020

3020 words 15 mins read

Paper Group ANR 774

Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT. Detecting Everyday Scenarios in Narrative Texts. Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network. Connecting and Comparing Language Model Interpolation Techniques. Translating neural signals to text using a Brain-Machine Interface. Infinit …

Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT


Title	Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT
Authors	James Butterworth, Rahul Savani, Karl Tuyls
Abstract	Simultaneous Localisation and Mapping (SLAM) algorithms are expensive to run on smaller robotic platforms such as Micro-Aerial Vehicles. Bug algorithms are an alternative that use relatively little processing power, and avoid high memory consumption by not building an explicit map of the environment. Bug Algorithms achieve relatively good performance in simulated and robotic maze solving domains. However, because they are hand-designed, a natural question is whether they are globally optimal control policies. In this work we explore the performance of Neuroevolution - specifically NEAT - at evolving control policies for simulated differential drive robots carrying out generalised maze navigation. We extend NEAT to include Gated Recurrent Units (GRUs) to help deal with long term dependencies. We show that both NEAT and our NEAT-GRU can repeatably generate controllers that outperform I-Bug (an algorithm particularly well-suited for use in real robots) on a test set of 209 indoor maze like environments. We show that NEAT-GRU is superior to NEAT in this task but also that out of the 2 systems, only NEAT-GRU can continuously evolve successful controllers for a much harder task in which no bearing information about the target is provided to the agent.
Tasks
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06239v1
PDF	http://arxiv.org/pdf/1904.06239v1.pdf
PWC	https://paperswithcode.com/paper/evolving-indoor-navigational-strategies-using
Repo
Framework

Detecting Everyday Scenarios in Narrative Texts


Title	Detecting Everyday Scenarios in Narrative Texts
Authors	Lilian D. A. Wanzare, Michael Roth, Manfred Pinkal
Abstract	Script knowledge consists of detailed information on everyday activities. Such information is often taken for granted in text and needs to be inferred by readers. Therefore, script knowledge is a central component to language comprehension. Previous work on representing scripts is mostly based on extensive manual work or limited to scenarios that can be found with sufficient redundancy in large corpora. We introduce the task of scenario detection, in which we identify references to scripts. In this task, we address a wide range of different scripts (200 scenarios) and we attempt to identify all references to them in a collection of narrative texts. We present a first benchmark data set and a baseline model that tackles scenario detection using techniques from topic segmentation and text classification.
Tasks	Text Classification
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04102v1
PDF	https://arxiv.org/pdf/1906.04102v1.pdf
PWC	https://paperswithcode.com/paper/detecting-everyday-scenarios-in-narrative
Repo
Framework


Title	Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
Authors	Weixia Zhang, Kede Ma, Jia Yan, Dexiang Deng, Zhou Wang
Abstract	We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions. Our model consists of two convolutional neural networks (CNN), each of which specializes in one distortion scenario. For synthetic distortions, we pre-train a CNN to classify image distortion type and level, where we enjoy large-scale training data. For authentic distortions, we adopt a pre-trained CNN for image classification. The features from the two CNNs are pooled bilinearly into a unified representation for final quality prediction. We then fine-tune the entire model on target subject-rated databases using a variant of stochastic gradient descent. Extensive experiments demonstrate that the proposed model achieves superior performance on both synthetic and authentic databases. Furthermore, we verify the generalizability of our method on the Waterloo Exploration Database using the group maximum differentiation competition.
Tasks	Blind Image Quality Assessment, Image Classification, Image Quality Assessment
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02665v1
PDF	https://arxiv.org/pdf/1907.02665v1.pdf
PWC	https://paperswithcode.com/paper/blind-image-quality-assessment-using-a-deep
Repo
Framework

Connecting and Comparing Language Model Interpolation Techniques


Title	Connecting and Comparing Language Model Interpolation Techniques
Authors	Ernest Pusateri, Christophe Van Gysel, Rami Botros, Sameer Badaskar, Mirko Hannemann, Youssef Oualil, Ilya Oparin
Abstract	In this work, we uncover a theoretical connection between two language model interpolation techniques, count merging and Bayesian interpolation. We compare these techniques as well as linear interpolation in three scenarios with abundant training data per component model. Consistent with prior work, we show that both count merging and Bayesian interpolation outperform linear interpolation. We include the first (to our knowledge) published comparison of count merging and Bayesian interpolation, showing that the two techniques perform similarly. Finally, we argue that other considerations will make Bayesian interpolation the preferred approach in most circumstances.
Tasks	Language Modelling
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09738v1
PDF	https://arxiv.org/pdf/1908.09738v1.pdf
PWC	https://paperswithcode.com/paper/connecting-and-comparing-language-model
Repo
Framework

Translating neural signals to text using a Brain-Machine Interface


Title	Translating neural signals to text using a Brain-Machine Interface
Authors	Janaki Sheth, Ariel Tankus, Michelle Tran, Nader Pouratian, Itzhak Fried, William Speier
Abstract	Brain-Computer Interfaces (BCI) help patients with faltering communication abilities due to neurodegenerative diseases produce text or speech output by direct neural processing. However, practical implementation of such a system has proven difficult due to limitations in speed, accuracy, and generalizability of the existing interfaces. To this end, we aim to create a BCI system that decodes text directly from neural signals. We implement a framework that initially isolates frequency bands in the input signal encapsulating differential information regarding production of various phonemic classes. These bands then form a feature set that feeds into an LSTM which discerns at each time point probability distributions across all phonemes uttered by a subject. Finally, these probabilities are fed into a particle filtering algorithm which incorporates prior knowledge of the English language to output text corresponding to the decoded word. Performance of this model on data obtained from six patients shows encouragingly high levels of accuracy at speeds and bit rates significantly higher than existing BCI communication systems. Further, in producing an output, our network abstains from constraining the reconstructed word to be from a given bag-of-words, unlike previous studies. The success of our proposed approach, offers promise for the employment of a BCI interface by patients in unfettered, naturalistic environments.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04265v1
PDF	https://arxiv.org/pdf/1907.04265v1.pdf
PWC	https://paperswithcode.com/paper/translating-neural-signals-to-text-using-a
Repo
Framework

Infinite Mixture Prototypes for Few-Shot Learning


Title	Infinite Mixture Prototypes for Few-Shot Learning
Authors	Kelsey R. Allen, Evan Shelhamer, Hanul Shin, Joshua B. Tenenbaum
Abstract	We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing prototypical methods that represent each class by a single cluster. By inferring the number of clusters, infinite mixture prototypes interpolate between nearest neighbor and prototypical representations, which improves accuracy and robustness in the few-shot regime. We show the importance of adaptive capacity for capturing complex data distributions such as alphabets, with 25% absolute accuracy improvements over prototypical networks, while still maintaining or improving accuracy on the standard Omniglot and mini-ImageNet benchmarks. In clustering labeled and unlabeled data by the same clustering rule, infinite mixture prototypes achieves state-of-the-art semi-supervised accuracy. As a further capability, we show that infinite mixture prototypes can perform purely unsupervised clustering, unlike existing prototypical methods.
Tasks	Few-Shot Learning, Omniglot
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04552v1
PDF	http://arxiv.org/pdf/1902.04552v1.pdf
PWC	https://paperswithcode.com/paper/infinite-mixture-prototypes-for-few-shot
Repo
Framework

Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations


Title	Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations
Authors	Zhoutong Wang, Qianhui Liang, Fabio Duarte, Fan Zhang, Louis Charron, Lenna Johnsen, Bill Cai, Carlo Ratti
Abstract	Legibility is the extent to which a space can be easily recognized. Evaluating legibility is particularly desirable in indoor spaces, since it has a large impact on human behavior and the efficiency of space utilization. However, indoor space legibility has only been studied through survey and trivial simulations and lacks reliable quantitative measurement. We utilized a Deep Convolutional Neural Network (DCNN), which is structurally similar to a human perception system, to model legibility in indoor spaces. To implement the modeling of legibility for any indoor spaces, we designed an end-to-end processing pipeline from indoor data retrieving to model training to spatial legibility analysis. Although the model performed very well (98% top-1 accuracy) overall, there are still discrepancies in accuracy among different spaces, reflecting legibility differences. To prove the validity of the pipeline, we deployed a survey on Amazon Mechanical Turk, collecting 4,015 samples. The human samples showed a similar behavior pattern and mechanism as the DCNN models. Further, we used model results to visually explain legibility in different architectural programs, building age, building style, visual clusterings of spaces and visual explanations for building age and architectural functions.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1901.10553v1
PDF	http://arxiv.org/pdf/1901.10553v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-legibility-of-indoor-spaces-using
Repo
Framework

Descriptive Dimensionality and Its Characterization of MDL-based Learning and Change Detection


Title	Descriptive Dimensionality and Its Characterization of MDL-based Learning and Change Detection
Authors	Kenji Yamanishi
Abstract	This paper introduces a new notion of dimensionality of probabilistic models from an information-theoretic view point. We call it the “descriptive dimension”(Ddim). We show that Ddim coincides with the number of independent parameters for the parametric class, and can further be extended to real-valued dimensionality when a number of models are mixed. The paper then derives the rate of convergence of the MDL (Minimum Description Length) learning algorithm which outputs a normalized maximum likelihood (NML) distribution with model of the shortest NML codelength. The paper proves that the rate is governed by Ddim. The paper also derives error probabilities of the MDL-based test for multiple model change detection. It proves that they are also governed by Ddim. Through the analysis, we demonstrate that Ddim is an intrinsic quantity which characterizes the performance of the MDL-based learning and change detection.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11540v1
PDF	https://arxiv.org/pdf/1910.11540v1.pdf
PWC	https://paperswithcode.com/paper/descriptive-dimensionality-and-its
Repo
Framework

Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system


Title	Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system
Authors	Victor Boutin, Angelo Franciosini, Frederic Chavane, Franck Ruffier, Laurent Perrinet
Abstract	Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to process context-dependent information in the early visual cortex. While numerous models have accounted for feedback effects at either neural or representational level, none of them were able to bind those two levels of analysis. Is it possible to describe feedback effects at both levels using the same model? We answer this question by combining Predictive Coding (PC) and Sparse Coding (SC) into a hierarchical and convolutional framework. In this Sparse Deep Predictive Coding (SDPC) model, the SC component models the internal recurrent processing within each layer, and the PC component describes the interactions between layers using feedforward and feedback connections. Here, we train a 2-layered SDPC on two different databases of images, and we interpret it as a model of the early visual system (V1 & V2). We first demonstrate that once the training has converged, SDPC exhibits oriented and localized receptive fields in V1 and more complex features in V2. Second, we analyze the effects of feedback on the neural organization beyond the classical receptive field of V1 neurons using interaction maps. These maps are similar to association fields and reflect the Gestalt principle of good continuation. We demonstrate that feedback signals reorganize interaction maps and modulate neural activity to promote contour integration. Third, we demonstrate at the representational level that the SDPC feedback connections are able to overcome noise in input images. Therefore, the SDPC captures the association field principle at the neural level which results in better disambiguation of blurred images at the representational level.
Tasks	Decision Making
Published	2019-02-20
URL	https://arxiv.org/abs/1902.07651v3
PDF	https://arxiv.org/pdf/1902.07651v3.pdf
PWC	https://paperswithcode.com/paper/meaningful-representations-emerge-from-sparse
Repo
Framework

Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic


Title	Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
Authors	Matteo Sordello, Weijie Su
Abstract	This paper proposes SplitSGD, a new stochastic optimization algorithm with a dynamic learning rate selection rule. This procedure decreases the learning rate for better adaptation to the local geometry of the objective function whenever a stationary phase is detected, that is, the iterates are likely to bounce around a vicinity of a local minimum. The detection is performed by splitting the single thread into two and using the inner products of the gradients from the two threads as a measure of stationarity. This learning rate selection is provably valid, robust to initial parameters, easy-to-implement, and essentially does not incur additional computational cost. Finally, we illustrate the robust convergence properties of SplitSGD through extensive experiments.
Tasks	Stochastic Optimization
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08597v3
PDF	https://arxiv.org/pdf/1910.08597v3.pdf
PWC	https://paperswithcode.com/paper/robust-learning-rate-selection-for-stochastic
Repo
Framework

Scalarizing Functions in Bayesian Multiobjective Optimization


Title	Scalarizing Functions in Bayesian Multiobjective Optimization
Authors	Tinkle Chugh
Abstract	Scalarizing functions have been widely used to convert a multiobjective optimization problem into a single objective optimization problem. However, their use in solving (computationally) expensive multi- and many-objective optimization problems in Bayesian multiobjective optimization is scarce. Scalarizing functions can play a crucial role on the quality and number of evaluations required when doing the optimization. In this article, we study and review 15 different scalarizing functions in the framework of Bayesian multiobjective optimization and build Gaussian process models (as surrogates, metamodels or emulators) on them. We use expected improvement as infill criterion (or acquisition function) to update the models. In particular, we compare different scalarizing functions and analyze their performance on several benchmark problems with different number of objectives to be optimized. The review and experiments on different functions provide useful insights when using and selecting a scalarizing function when using a Bayesian multiobjective optimization method.
Tasks	Multiobjective Optimization
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05760v1
PDF	http://arxiv.org/pdf/1904.05760v1.pdf
PWC	https://paperswithcode.com/paper/scalarizing-functions-in-bayesian
Repo
Framework

Neuroevolution with Perceptron Turing Machines


Title	Neuroevolution with Perceptron Turing Machines
Authors	David Landaeta
Abstract	We introduce the perceptron Turing machine and show how it can be used to create a system of neuroevolution. Advantages of this approach include automatic scaling of solutions to larger problem sizes, the ability to experiment with hand-coded solutions, and an enhanced potential for understanding evolved solutions. Hand-coded solutions may be implemented in the low-level language of Turing machines, which is the genotype used in neuroevolution, but a high-level language called Lopro is introduced to make the job easier.
Tasks
Published	2019-01-30
URL	http://arxiv.org/abs/1901.11090v1
PDF	http://arxiv.org/pdf/1901.11090v1.pdf
PWC	https://paperswithcode.com/paper/neuroevolution-with-perceptron-turing
Repo
Framework

Discovering seminal works with marker papers


Title	Discovering seminal works with marker papers
Authors	Robin Haunschild, Werner Marx
Abstract	Bibliometric information retrieval in databases can employ different strategies. Com-monly, queries are performed by searching in title, abstract and/or author keywords (author vocabulary). More advanced queries employ database keywords to search in a controlled vo-cabulary. Queries based on search terms can be augmented with their citing papers if a re-search field cannot be curtailed by the search query alone. Here, we present another strategy to discover the most important papers of a research field. A marker paper is used to reveal the most important works for the relevant community. All papers co-cited with the marker paper are analyzed using reference publication year spectroscopy (RPYS). For demonstration of the marker paper approach, density functional theory (DFT) is used as a research field. Compari-sons between a prior RPYS on a publication set compiled using a keyword-based search in a controlled vocabulary and three different co-citation RPYS (RPYS-CO) analyses show very similar results. Similarities and differences are discussed.
Tasks	Information Retrieval
Published	2019-01-22
URL	https://arxiv.org/abs/1901.07352v4
PDF	https://arxiv.org/pdf/1901.07352v4.pdf
PWC	https://paperswithcode.com/paper/discovering-seminal-works-with-marker-papers
Repo
Framework

Bayesian Optimization with Binary Auxiliary Information


Title	Bayesian Optimization with Binary Auxiliary Information
Authors	Yehong Zhang, Zhongxiang Dai, Kian Hsiang Low
Abstract	This paper presents novel mixed-type Bayesian optimization (BO) algorithms to accelerate the optimization of a target objective function by exploiting correlated auxiliary information of binary type that can be more cheaply obtained, such as in policy search for reinforcement learning and hyperparameter tuning of machine learning models with early stopping. To achieve this, we first propose a mixed-type multi-output Gaussian process (MOGP) to jointly model the continuous target function and binary auxiliary functions. Then, we propose information-based acquisition functions such as mixed-type entropy search (MT-ES) and mixed-type predictive ES (MT-PES) for mixed-type BO based on the MOGP predictive belief of the target and auxiliary functions. The exact acquisition functions of MT-ES and MT-PES cannot be computed in closed form and need to be approximated. We derive an efficient approximation of MT-PES via a novel mixed-type random features approximation of the MOGP model whose cross-correlation structure between the target and auxiliary functions can be exploited for improving the belief of the global target maximizer using observations from evaluating these functions. We propose new practical constraints to relate the global target maximizer to the binary auxiliary functions. We empirically evaluate the performance of MT-ES and MT-PES with synthetic and real-world experiments.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07277v1
PDF	https://arxiv.org/pdf/1906.07277v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-with-binary-auxiliary
Repo
Framework

Semantic-Aware Label Placement for Augmented Reality in Street View


Title	Semantic-Aware Label Placement for Augmented Reality in Street View
Authors	Jianqing Jia, Semir Elezovikj, Heng Fan, Shuojin Yang, Jing Liu, Wei Guo, Chiu C. Tan, Haibin Ling
Abstract	In an augmented reality (AR) application, placing labels in a manner that is clear and readable without occluding the critical information from the real-world can be a challenging problem. This paper introduces a label placement technique for AR used in street view scenarios. We propose a semantic-aware task-specific label placement method by identifying potentially important image regions through a novel feature map, which we refer to as guidance map. Given an input image, its saliency information, semantic information and the task-specific importance prior are integrated into the guidance map for our labeling task. To learn the task prior, we created a label placement dataset with the users’ labeling preferences, as well as use it for evaluation. Our solution encodes the constraints for placing labels in an optimization problem to obtain the final label layout, and the labels will be placed in appropriate positions to reduce the chances of overlaying important real-world objects in street view AR scenarios. The experimental validation shows clearly the benefits of our method over previous solutions in the AR street view navigation and similar applications.
Tasks
Published	2019-12-15
URL	https://arxiv.org/abs/1912.07105v1
PDF	https://arxiv.org/pdf/1912.07105v1.pdf
PWC	https://paperswithcode.com/paper/semantic-aware-label-placement-for-augmented
Repo
Framework