July 29, 2019

3103 words 15 mins read

Paper Group ANR 140

Center of Gravity PSO for Partitioning Clustering. Approximate Bayesian inference as a gauge theory. Flexible Network Binarization with Layer-wise Priority. Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection. Model Complexity-Accuracy Trade-off for a Convolutional Neural Network. Neural Attribute Machines for Pro …

Center of Gravity PSO for Partitioning Clustering


Title	Center of Gravity PSO for Partitioning Clustering
Authors	Shahira Shaaban Azab, Hesham Ahmed Hefny
Abstract	This paper presents the local best model of PSO for partition-based clustering. The proposed model gets rid off the drawbacks of gbest PSO for clustering. The model uses a pre-specified number of clusters K. The LPOSC has K neighborhoods. Each neighborhood represents one of the clusters. The goal of the particles in each neighborhood is optimizing the position of the centroid of the cluster. The performance of the proposed algorithms is measured using adjusted rand index. The results is compared with k-means and global best model of PSO.
Tasks
Published	2017-06-03
URL	http://arxiv.org/abs/1706.00997v2
PDF	http://arxiv.org/pdf/1706.00997v2.pdf
PWC	https://paperswithcode.com/paper/center-of-gravity-pso-for-partitioning
Repo
Framework

Approximate Bayesian inference as a gauge theory


Title	Approximate Bayesian inference as a gauge theory
Authors	Biswa Sengupta, Karl Friston
Abstract	In a published paper [Sengupta, 2016], we have proposed that the brain (and other self-organized biological and artificial systems) can be characterized via the mathematical apparatus of a gauge theory. The picture that emerges from this approach suggests that any biological system (from a neuron to an organism) can be cast as resolving uncertainty about its external milieu, either by changing its internal states or its relationship to the environment. Using formal arguments, we have shown that a gauge theory for neuronal dynamics – based on approximate Bayesian inference – has the potential to shed new light on phenomena that have thus far eluded a formal description, such as attention and the link between action and perception. Here, we describe the technical apparatus that enables such a variational inference on manifolds. Particularly, the novel contribution of this paper is an algorithm that utlizes a Schild’s ladder for parallel transport of sufficient statistics (means, covariances, etc.) on a statistical manifold.
Tasks	Bayesian Inference
Published	2017-05-17
URL	http://arxiv.org/abs/1705.06614v2
PDF	http://arxiv.org/pdf/1705.06614v2.pdf
PWC	https://paperswithcode.com/paper/approximate-bayesian-inference-as-a-gauge
Repo
Framework

Flexible Network Binarization with Layer-wise Priority


Title	Flexible Network Binarization with Layer-wise Priority
Authors	Lixue Zhuang, Yi Xu, Bingbing Ni, Hongteng Xu
Abstract	How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the compression ratio of network and the loss of performance. Based on this fact, we propose a novel and flexible neural network binarization method by introducing the concept of layer-wise priority which binarizes parameters in inverse order of their layer depth. In each training step, our method selects a specific network layer, minimizes the discrepancy between the original real-valued weights and its binary approximations, and fine-tunes the whole network accordingly. During the iteration of the above process, it is significant that we can flexibly decide whether to binarize the remaining floating layers or not and explore a trade-off between the loss of performance and the compression ratio of model. The resulting binary network is applied for efficient pedestrian detection. Extensive experimental results on several benchmarks show that under the same compression ratio, our method achieves much lower miss rate and faster detection speed than the state-of-the-art neural network binarization method.
Tasks	Pedestrian Detection
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04344v3
PDF	http://arxiv.org/pdf/1709.04344v3.pdf
PWC	https://paperswithcode.com/paper/flexible-network-binarization-with-layer-wise
Repo
Framework

Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection


Title	Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection
Authors	Sadique Sheik, Somnath Paul, Charles Augustine, Gert Cauwenberghs
Abstract	Several learning rules for synaptic plasticity, that depend on either spike timing or internal state variables, have been proposed in the past imparting varying computational capabilities to Spiking Neural Networks. Due to design complications these learning rules are typically not implemented on neuromorphic devices leaving the devices to be only capable of inference. In this work we propose a unidirectional post-synaptic potential dependent learning rule that is only triggered by pre-synaptic spikes, and easy to implement on hardware. We demonstrate that such a learning rule is functionally capable of replicating computational capabilities of pairwise STDP. Further more, we demonstrate that this learning rule can be used to learn and classify spatio-temporal spike patterns in an unsupervised manner using individual neurons. We argue that this learning rule is computationally powerful and also ideal for hardware implementations due to its unidirectional memory access.
Tasks
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01495v1
PDF	http://arxiv.org/pdf/1701.01495v1.pdf
PWC	https://paperswithcode.com/paper/membrane-dependent-neuromorphic-learning-rule
Repo
Framework

Model Complexity-Accuracy Trade-off for a Convolutional Neural Network


Title	Model Complexity-Accuracy Trade-off for a Convolutional Neural Network
Authors	Atul Dhingra
Abstract	Convolutional Neural Networks(CNN) has had a great success in the recent past, because of the advent of faster GPUs and memory access. CNNs are really powerful as they learn the features from data in layers such that they exhibit the structure of the V-1 features of the human brain. A huge bottleneck, in this case, is that CNNs are very large and have a very high memory footprint, and hence they cannot be employed on devices with limited storage such as mobile phone, IoT etc. In this work, we study the model complexity versus accuracy trade-off on MNSIT dataset, and give a concrete framework for handling such a problem, given the worst case accuracy that a system can tolerate. In our work, we reduce the model complexity by 236 times, and memory footprint by 19.5 times compared to the base model while achieving worst case accuracy threshold.
Tasks
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03338v1
PDF	http://arxiv.org/pdf/1705.03338v1.pdf
PWC	https://paperswithcode.com/paper/model-complexity-accuracy-trade-off-for-a
Repo
Framework

Neural Attribute Machines for Program Generation


Title	Neural Attribute Machines for Program Generation
Authors	Matthew Amodio, Swarat Chaudhuri, Thomas Reps
Abstract	Recurrent neural networks have achieved remarkable success at generating sequences with complex structures, thanks to advances that include richer embeddings of input and cures for vanishing gradients. Trained only on sequences from a known grammar, though, they can still struggle to learn rules and constraints of the grammar. Neural Attribute Machines (NAMs) are equipped with a logical machine that represents the underlying grammar, which is used to teach the constraints to the neural machine by (i) augmenting the input sequence, and (ii) optimizing a custom loss function. Unlike traditional RNNs, NAMs are exposed to the grammar, as well as samples from the language of the grammar. During generation, NAMs make significantly fewer violations of the constraints of the underlying grammar than RNNs trained only on samples from the language of the grammar.
Tasks
Published	2017-05-25
URL	http://arxiv.org/abs/1705.09231v2
PDF	http://arxiv.org/pdf/1705.09231v2.pdf
PWC	https://paperswithcode.com/paper/neural-attribute-machines-for-program
Repo
Framework

ASDA : Analyseur Syntaxique du Dialecte Alg{é}rien dans un but d’analyse s{é}mantique


Title	ASDA : Analyseur Syntaxique du Dialecte Alg{é}rien dans un but d’analyse s{é}mantique
Authors	Imène Guellil, Faiçal Azouaou
Abstract	Opinion mining and sentiment analysis in social media is a research issue having a great interest in the scientific community. However, before begin this analysis, we are faced with a set of problems. In particular, the problem of the richness of languages and dialects within these media. To address this problem, we propose in this paper an approach of construction and implementation of Syntactic analyzer named ASDA. This tool represents a parser for the Algerian dialect that label the terms of a given corpus. Thus, we construct a labeling table containing for each term its stem, different prefixes and suffixes, allowing us to determine the different grammatical parts a sort of POS tagging. This labeling will serve us later in the semantic processing of the Algerian dialect, like the automatic translation of this dialect or sentiment analysis
Tasks	Opinion Mining, Sentiment Analysis
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08998v1
PDF	http://arxiv.org/pdf/1707.08998v1.pdf
PWC	https://paperswithcode.com/paper/asda-analyseur-syntaxique-du-dialecte
Repo
Framework

Text Extraction From Texture Images Using Masked Signal Decomposition


Title	Text Extraction From Texture Images Using Masked Signal Decomposition
Authors	Shervin Minaee, Yao Wang
Abstract	Text extraction is an important problem in image processing with applications from optical character recognition to autonomous driving. Most of the traditional text segmentation algorithms consider separating text from a simple background (which usually has a different color from texts). In this work we consider separating texts from a textured background, that has similar color to texts. We look at this problem from a signal decomposition perspective, and consider a more realistic scenario where signal components are overlaid on top of each other (instead of adding together). When the signals are overlaid, to separate signal components, we need to find a binary mask which shows the support of each component. Because directly solving the binary mask is intractable, we relax this problem to the approximated continuous problem, and solve it by alternating optimization method. We show that the proposed algorithm achieves significantly better results than other recent works on several challenging images.
Tasks	Autonomous Driving, Optical Character Recognition
Published	2017-06-11
URL	http://arxiv.org/abs/1706.04041v3
PDF	http://arxiv.org/pdf/1706.04041v3.pdf
PWC	https://paperswithcode.com/paper/text-extraction-from-texture-images-using
Repo
Framework

Cross-lingual, Character-Level Neural Morphological Tagging


Title	Cross-lingual, Character-Level Neural Morphological Tagging
Authors	Ryan Cotterell, Georg Heigold
Abstract	Even for common NLP tasks, sufficient supervision is not available in many languages – morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30%
Tasks	Morphological Tagging, Transfer Learning
Published	2017-08-30
URL	https://arxiv.org/abs/1708.09157v3
PDF	https://arxiv.org/pdf/1708.09157v3.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-character-level-neural
Repo
Framework

Robust Optical Flow Estimation in Rainy Scenes


Title	Robust Optical Flow Estimation in Rainy Scenes
Authors	Ruoteng Li, Robby T. Tan, Loong-Fah Cheong
Abstract	Optical flow estimation in the rainy scenes is challenging due to background degradation introduced by rain streaks and rain accumulation effects in the scene. Rain accumulation effect refers to poor visibility of remote objects due to the intense rainfall. Most existing optical flow methods are erroneous when applied to rain sequences because the conventional brightness constancy constraint (BCC) and gradient constancy constraint (GCC) generally break down in this situation. Based on the observation that the RGB color channels receive raindrop radiance equally, we introduce a residue channel as a new data constraint to reduce the effect of rain streaks. To handle rain accumulation, our method decomposes the image into a piecewise-smooth background layer and a high-frequency detail layer. It also enforces the BCC on the background layer only. Results on both synthetic dataset and real images show that our algorithm outperforms existing methods on different types of rain sequences. To our knowledge, this is the first optical flow method specifically dealing with rain.
Tasks	Optical Flow Estimation
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05239v2
PDF	http://arxiv.org/pdf/1704.05239v2.pdf
PWC	https://paperswithcode.com/paper/robust-optical-flow-estimation-in-rainy
Repo
Framework

Learning local trajectories for high precision robotic tasks : application to KUKA LBR iiwa Cartesian positioning


Title	Learning local trajectories for high precision robotic tasks : application to KUKA LBR iiwa Cartesian positioning
Authors	Joris Guerin, Olivier Gibaru, Eric Nyiri, Stephane Thiery
Abstract	To ease the development of robot learning in industry, two conditions need to be fulfilled. Manipulators must be able to learn high accuracy and precision tasks while being safe for workers in the factory. In this paper, we extend previously submitted work which consists in rapid learning of local high accuracy behaviors. By exploration and regression, linear and quadratic models are learnt for respectively the dynamics and cost function. Iterative Linear Quadratic Gaussian Regulator combined with cost quadratic regression can converge rapidly in the final stages towards high accuracy behavior as the cost function is modelled quite precisely. In this paper, both a different cost function and a second order improvement method are implemented within this framework. We also propose an analysis of the algorithm parameters through simulation for a positioning task. Finally, an experimental validation on a KUKA LBR iiwa robot is carried out. This collaborative robot manipulator can be easily programmed into safety mode, which makes it qualified for the second industry constraint stated above.
Tasks
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01497v1
PDF	http://arxiv.org/pdf/1701.01497v1.pdf
PWC	https://paperswithcode.com/paper/learning-local-trajectories-for-high
Repo
Framework

Long Timescale Credit Assignment in NeuralNetworks with External Memory


Title	Long Timescale Credit Assignment in NeuralNetworks with External Memory
Authors	Steven Stenberg Hansen
Abstract	Credit assignment in traditional recurrent neural networks usually involves back-propagating through a long chain of tied weight matrices. The length of this chain scales linearly with the number of time-steps as the same network is run at each time-step. This creates many problems, such as vanishing gradients, that have been well studied. In contrast, a NNEM’s architecture recurrent activity doesn’t involve a long chain of activity (though some architectures such as the NTM do utilize a traditional recurrent architecture as a controller). Rather, the externally stored embedding vectors are used at each time-step, but no messages are passed from previous time-steps. This means that vanishing gradients aren’t a problem, as all of the necessary gradient paths are short. However, these paths are extremely numerous (one per embedding vector in memory) and reused for a very long time (until it leaves the memory). Thus, the forward-pass information of each memory must be stored for the entire duration of the memory. This is problematic as this additional storage far surpasses that of the actual memories, to the extent that large memories on infeasible to back-propagate through in high dimensional settings. One way to get around the need to hold onto forward-pass information is to recalculate the forward-pass whenever gradient information is available. However, if the observations are too large to store in the domain of interest, direct reinstatement of a forward pass cannot occur. Instead, we rely on a learned autoencoder to reinstate the observation, and then use the embedding network to recalculate the forward-pass. Since the recalculated embedding vector is unlikely to perfectly match the one stored in memory, we try out 2 approximations to utilize error gradient w.r.t. the vector in memory.
Tasks
Published	2017-01-14
URL	http://arxiv.org/abs/1701.03866v1
PDF	http://arxiv.org/pdf/1701.03866v1.pdf
PWC	https://paperswithcode.com/paper/long-timescale-credit-assignment-in
Repo
Framework

An experimental study of graph-based semi-supervised classification with additional node information


Title	An experimental study of graph-based semi-supervised classification with additional node information
Authors	Bertrand Lebichot, Marco Saerens
Abstract	The volume of data generated by internet and social networks is increasing every day, and there is a clear need for efficient ways of extracting useful information from them. As those data can take different forms, it is important to use all the available data representations for prediction. In this paper, we focus our attention on supervised classification using both regular plain, tabular, data and structural information coming from a network structure. 14 techniques are investigated and compared in this study and can be divided in three classes: the first one uses only the plain data to build a classification model, the second uses only the graph structure and the last uses both information sources. The relative performances in these three cases are investigated. Furthermore, the effect of using a graph embedding and well-known indicators in spatial statistics is also studied. Possible applications are automatic classification of web pages or other linked documents, of people in a social network or of proteins in a biological complex system, to name a few. Based on our comparison, we draw some general conclusions and advices to tackle this particular classification task: some datasets can be better explained by their graph structure (graph-driven), or by their feature set (features-driven). The most efficient methods are discussed in both cases.
Tasks	Graph Embedding
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08716v1
PDF	http://arxiv.org/pdf/1705.08716v1.pdf
PWC	https://paperswithcode.com/paper/an-experimental-study-of-graph-based-semi
Repo
Framework

Local Gaussian Processes for Efficient Fine-Grained Traffic Speed Prediction


Title	Local Gaussian Processes for Efficient Fine-Grained Traffic Speed Prediction
Authors	Truc Viet Le, Richard J. Oentaryo, Siyuan Liu, Hoong Chuin Lau
Abstract	Traffic speed is a key indicator for the efficiency of an urban transportation system. Accurate modeling of the spatiotemporally varying traffic speed thus plays a crucial role in urban planning and development. This paper addresses the problem of efficient fine-grained traffic speed prediction using big traffic data obtained from static sensors. Gaussian processes (GPs) have been previously used to model various traffic phenomena, including flow and speed. However, GPs do not scale with big traffic data due to their cubic time complexity. In this work, we address their efficiency issues by proposing local GPs to learn from and make predictions for correlated subsets of data. The main idea is to quickly group speed variables in both spatial and temporal dimensions into a finite number of clusters, so that future and unobserved traffic speed queries can be heuristically mapped to one of such clusters. A local GP corresponding to that cluster can then be trained on the fly to make predictions in real-time. We call this method localization. We use non-negative matrix factorization for localization and propose simple heuristics for cluster mapping. We additionally leverage on the expressiveness of GP kernel functions to model road network topology and incorporate side information. Extensive experiments using real-world traffic data collected in the two U.S. cities of Pittsburgh and Washington, D.C., show that our proposed local GPs significantly improve both runtime performances and prediction accuracies compared to the baseline global and local GPs.
Tasks	Gaussian Processes
Published	2017-08-27
URL	http://arxiv.org/abs/1708.08079v1
PDF	http://arxiv.org/pdf/1708.08079v1.pdf
PWC	https://paperswithcode.com/paper/local-gaussian-processes-for-efficient-fine
Repo
Framework

Improving Vision-based Self-positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection


Title	Improving Vision-based Self-positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection
Authors	Parag S. Chandakkar, Yilin Wang, Baoxin Li
Abstract	Traffic congestion is a widespread problem. Dynamic traffic routing systems and congestion pricing are getting importance in recent research. Lane prediction and vehicle density estimation is an important component of such systems. We introduce a novel problem of vehicle self-positioning which involves predicting the number of lanes on the road and vehicle’s position in those lanes using videos captured by a dashboard camera. We propose an integrated closed-loop approach where we use the presence of vehicles to aid the task of self-positioning and vice-versa. To incorporate multiple factors and high-level semantic knowledge into the solution, we formulate this problem as a Bayesian framework. In the framework, the number of lanes, the vehicle’s position in those lanes and the presence of other vehicles are considered as parameters. We also propose a bounding box selection scheme to reduce the number of false detections and increase the computational efficiency. We show that the number of box proposals decreases by a factor of 6 using the selection approach. It also results in large reduction in the number of false detections. The entire approach is tested on real-world videos and is found to give acceptable results.
Tasks	Density Estimation
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01256v1
PDF	http://arxiv.org/pdf/1704.01256v1.pdf
PWC	https://paperswithcode.com/paper/improving-vision-based-self-positioning-in
Repo
Framework