检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Sledge, Isaac J. Bryner, Darshan W. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Branch Head of the Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL32407 United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States The Computational NeuroEngineering Laboratory University of Florida United States

Reinforcement learning in large-scale environments is challenging due to the many possible actions that can be taken in specific situations. We have previously developed a means of constraining, and hence speeding up, the search process through the use of motion primitives;motion primitives are sequences of pre-specified actions taken across a state series. As a byproduct of this work, we have found that if the motion primitives' motions and actions are labeled, then the search can be sped up further. Since motion primitives may initially lack such details, we propose a theoretically viewpoint-insensitive and speed-insensitive means of automatically annotating the underlying motions and actions. We do this through a differential-geometric, spatio-temporal kinematics descriptor, which analyzes how the poses of entities in two motion sequences change over time. We use this descriptor in conjunction with a weighted-nearest-neighbor classifier to label the primitives using a limited set of training examples. In our experiments, we achieve high motion and action annotation rates for human-action-derived primitives with as few as one training sample. We also demonstrate that reinforcement learning using accurately labeled trajectories leads to high-performing policies more quickly than standard reinforcement learning techniques. This is partly because motion primitives encode prior domain knowledge and preempt the need to re-discover that knowledge during training. It is also because agents can leverage the labels to systematically ignore action classes that do not facilitate task objectives, thereby reducing the action space. © 2021, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An information-theoretic approach for automatically determining the number of state groups when aggregating markov chains

arXiv

引用

arXiv 2021年

作者： Sledge, Isaac J. Príncipe, José C. Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama City United States Department of Electrical and Computer Engineering University of Florida Department of Biomedical Engineering University of Florida

A fundamental problem when aggregating Markov chains is the specification of the number of state groups. Too few state groups may fail to sufficiently capture the pertinent dynamics of the original, high-order Markov chain. Too many state groups may lead to a non-parsimonious, reduced-order Markov chain whose complexity rivals that of the original. In this paper, we show that an augmented value-of-information-based approach to aggregating Markov chains facilitates the determination of the number of state groups. The optimal state-group count coincides with the case where the complexity of the reduced-order chain is balanced against the mutual dependence between the original- and reduced-order chain dynamics. © 2021, CC BY.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Sledge, Isaac J. Príncipe, José C. Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States lab The Naval Sea Systems Command United States Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States The University of Florida United States

In this paper, we consider the problem of adjusting the exploration rate when using value-of-information-based exploration. We do this by converting the value-of-information optimization into a problem of finding equilibria of a flow for a changing exploration rate. We then develop an efficient pathfollowing scheme for converging to these equilibria and hence uncovering optimal action-selection policies. Under this scheme, the exploration rate is automatically adapted according to the agent’s experiences. Global convergence is theoretically assured. We first evaluate our exploration-rate adaptation on the Nintendo GameBoy games Centipede and Millipede. We demonstrate aspects of the search process, like that it yields a hierarchy of state abstractions. We also show that our approach returns better policies in fewer episodes than conventional search strategies relying on heuristic, annealing-based exploration-rate adjustments. We then illustrate that these trends hold for deep, value-of-information-based agents that learn to play ten simple games and over forty more complicated games for the Nintendo GameBoy system. Performance either near or well above the level of human play is observed. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

External-memory networks for low-shot learning of targets in forward-looking-sonar imagery

arXiv

引用

arXiv 2021年

作者： Sledge, Isaac J. Toole, Christopher D. Maestri, Joseph A. Príncipe, José C. Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States Signal Processing and Analysis Branch Naval Undersea Warfare Center NewportRI United States Department of Electrical and Computer Engineering Department of Biomedical Engineering University of Florida GainesvilleFL United States

We propose a memory-based framework for real-time, data-efficient target analysis in forward-looking-sonar (FLS) imagery. Our framework relies on first removing non-discriminative details from the imagery using a small-scale DENSENET-inspired network. Doing so simplifies ensuing analyses and permits generalizing from few labeled *** then cascade the filtered imagery into a novel NEURALRAM-based convolutional matching network, NRMN, for low-shot target *** employ a small-scale FLOWNET, LFN to align and register FLS imagery across local temporal scales. LFN enables target label consensus voting across images and generally improves target detection and recognition rates. We evaluate our framework using real-world FLS imagery with multiple broad target classes that have high intra-class variability and rich sub-class *** show that few-shot learning, with anywhere from ten to thirty class-specific exemplars, performs similarly to supervised deep networks trained on hundreds of samples per class. Effective zero-shot learning is also possible. High performance is realized from the inductive-transfer properties of NRMNs when distractor elements are removed. © 2021, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Estimating Rényi's α-cross-entropies in a matrix-based way

arXiv

引用

arXiv 2021年

作者： Sledge, Isaac J. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL United States

Conventional information-theoretic quantities assume access to probability distributions. Estimating such distributions is not trivial. Here, we consider function-based formulations of cross entropy that sidesteps this a priori estimation requirement. We propose three measures of Rényi's α-cross-entropies in the setting of reproducing-kernel Hilbert spaces. Each measure has its appeals. We prove that we can estimate these measures in an unbiased, non-parametric, and minimax-optimal way. We do this via sample-constructed Gram matrices. This yields matrix-based estimators of Rényi's α-cross-entropies. These estimators satisfy all of the axioms that Rényi established for divergences. Our cross-entropies can thus be used for assessing distributional differences. They are also appropriate for handling high-dimensional distributions, since the convergence rate of our estimator is independent of the sample dimensionality. Python code for implementing these measures can be found at https://***/isledge/MBRCE. © 2021, CC BY.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Semantic Segmentation of Circular-Scan, Synthetic-Aperture-Sonar Imagery

arXiv

引用

arXiv 2024年

作者： Sledge, Isaac J. Byrne, Dominic M. King, Jonathan L. Ostertag, Steven H. Woods, Denton L. Prater, James L. Kennedy, Jermaine L. Marston, Timothy M. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Naval Sea Systems Command United States The Applied Sensing and Processing Branch Naval Surface Warfare Center Panama CityFL United States The Littoral Acoustics and Target Physics Branch Naval Surface Warfare Center Panama CityFL United States The Division Head of the Sensing Sciences and Systems Division Naval Surface Warfare Center Panama CityFL United States The Applied Physics Laboratory University of Washington SeattleWA United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL United States The University of Florida United States

We propose a weakly-supervised framework for the semantic segmentation of circular-scan synthetic-aperture-sonar (CSAS) imagery. The first part of our framework is trained in a supervised manner, on image-level labels, to uncover a set of semi-sparse, spatially-discriminative regions in each image. The classification uncertainty of each region is then evaluated. Those areas with the lowest uncertainties are then chosen to be weakly labeled segmentation seeds, at the pixel level, for the second part of the framework. Each of the seed extents are progressively resized according to an unsupervised, information-theoretic loss with structured-prediction regularizers. This reshaping process uses multi-scale, adaptively-weighted features to delineate class-specific transitions in local image content. Content-addressable memories are inserted at various parts of our framework so that it can leverage features from previously seen images to improve segmentation performance for related images. We evaluate our weakly-supervised framework using real-world CSAS imagery that contains over ten seafloor classes and ten target classes. We show that our framework performs comparably to nine fully-supervised deep networks. Our framework also outperforms eleven of the best weakly-supervised deep networks. We achieve state-of-the-art performance when pre-training on natural imagery. The average absolute performance gap to the next-best weakly-supervised network is well over ten percent for both natural imagery and sonar imagery. This gap is found to be statistically significant. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Faster convergence in deep-predictive-coding networks to learn deeper representations

arXiv

引用

arXiv 2021年

作者： Sledge, Isaac J. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Department of Electrical and Computer Engineering University of Florida GainesvilleFL United States The Department of Biomedical Engineering University of Florida GainesvilleFL United States

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse, invariant features. However, this inference is a major computational bottleneck. It severely limits the network depth due to learning stagnation. Here, we prove why this bottleneck occurs. We then propose a new forward-inference strategy based on accelerated proximal gradients. This strategy has faster theoretical convergence guarantees than the one used for DPCNs. It overcomes learning stagnation. We also demonstrate that it permits constructing deep and wide predictive-coding networks. Such convolutional networks implement receptive fields that capture well the entire classes of objects on which the networks are trained. This improves the feature representations compared with our lab's previous non-convolutional and convolutional DPCNs. It yields unsupervised object recognition that surpass convolutional autoencoders and are on par with convolutional networks trained in a supervised manner. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Regularized Training of Convolutional Autoencoders using the Rényi-Stratonovich Value of Information

Regularized Training of Convolutional Autoencoders using the...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Isaac J. Sledge José C. Príncipe Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Department of Electrical and Computer Engineering University of Florida Department of Biomedical Engineering University of Florida

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

We propose an information-theoretic cost function or the regularized training of convolutional auto encoders that imposes an organization on the bottleneck-layer-projected samples so as to facilitate discrimination. This function is based on a continuous-space, Rényi-mutual-information version of Stratonovich's value of information. It quantifies the maximum benefit that can be obtained for a given bottleneck-layer representation compression amount. The compression amount is controlled by a single hyperparameter that trades off between the autoencoder reconstruction quality and the hidden-layer representation uncertainty.

关键词： Random variables Training Encoding Uncertainty Entropy Mutual information Organizations

来源：评论

学校读者我要写书评

暂无评论

Deep Radar Sensor Models for Accurate and Robust Object Tracking

Deep Radar Sensor Models for Accurate and Robust Object Trac...

引用

International Conference on Intelligent Transportation

作者： Jasmin Ebert Thomas Gumpp Sebastian Münzner Alex Matskevych Alexandru P. Condurache Claudius Gläser Engineering Cognitive Systems Automated Driving Chassis Systems Control Robert Bosch GmbH Leonberg Germany Advanced Autonomous Systems Corporate Research Robert Bosch GmbH Renningen Germany Institute for Signal Processing University of Lübeck Germany

ISBN: (数字)9781728141497

ISBN: (纸本)9781728141503

Object tracking is one of the key challenges for perception systems of autonomous vehicles. Recursive Bayesian state estimation can be used to obtain object tracks. Both the measurement association and the object update within such Bayesian filters rely on sensor measurement models. These models offer an approximation of the expected sensor values that can be error-prone due to a mismatch between model and reality. The discrepancy is caused by the limited descriptive capacity of measurement models since sensor measurements are highly object and situation dependent. We address this problem in a data-driven approach by using Deep Neural Networks (DNNs) to learn situation dependent sensor measurement models. In detail, the DNN acts as a virtual sensor that uses current sensor measurements to regress necessary corrections of predicted object states. It can be directly plugged into existing tracking frameworks, substituting the previously hand-modeled association and update steps during Bayesian Filtering. We apply the proposed DNN-based measurement models to the problem of vehicle tracking using radar data in an Extended Kalman Filter setup and compare it to a classical closest reflex and an L-shape measurement update model. Extensive evaluation on a real-world dataset shows that our model improves performances significantly compared to state of the art methods.

关键词： Radar tracking Current measurement Radar Radar measurements Kalman filters Noise measurement Measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Target detection and segmentation in circular-scan synthetic-aperture-sonar images using semi-supervised convolutional encoder-decoders

arXiv

引用

arXiv 2021年

作者： Sledge, Isaac J. Emigh, Matthew S. King, Jonathan L. Woods, Denton L. Tory Cobb, J. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL32407 United States The Applied Sensing and Processing Branch Naval Surface Warfare Center Panama CityFL32407 United States The Littoral Acoustics and Target Physics Branch Naval Surface Warfare Center Panama CityFL32407 United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States

We propose a framework for saliency-based, multi-target detection and segmentation of circular-scan, synthetic-aperture-sonar (CSAS) imagery. Our framework relies on a multi-branch, convolutional encoder-decoder network (MB-CEDN). The encoder portion of the MB-CEDN extracts visual contrast features from CSAS images. These features are fed into dual decoders that perform pixel-level segmentation to mask targets. Each decoder provides different perspectives as to what constitutes a salient target. These opinions are aggregated and cascaded into a deep-parsing network to refine the segmentation. We evaluate our framework using real-world CSAS imagery consisting of five broad target classes. We compare against existing approaches from the computer-vision literature. We show that our framework outperforms supervised, deep-saliency networks designed for natural imagery. It greatly outperforms unsupervised saliency approaches developed for natural imagery. This illustrates that natural-image-based models may need to be altered to be effective for this imaging-sonar modality. © 2021, CC BY.

关键词： Sonar

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：