检索结果-内蒙古大学图书馆

Efficient and Robust Machine Learning for Real-World Systems

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Pernkopf, Franz Roth, Wolfgang Zöhrer, Matthias Pfeifenberger, Lukas Schindler, Günther Fröning, Holger Tschiatschek, Sebastian Peharz, Robert Mattina, Matthew Ghahramani, Zoubin Department of Electrical Engineering Laboratory of Signal Processing and Speech Communication Graz University of Technology Austria Institute of Computer Engineering Ruperts Karls University Heidelberg Germany Microsoft Research Cambridge United Kingdom Machine Learning Group Department of Engineering University of Cambridge United Kingdom Machine Learning Group Department of Engineering University of Cambridge United Kingdom Uber AI Labs CA United States Arm Research Arm Ltd. Cambridge United Kingdom

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully chosen tradeoff between performance and resource consumption in terms of computation and energy. On top of this, it is crucial to treat uncertainty in a consistent manner in all but the simplest applications of machine learning systems. In particular, a desideratum for any real-world system is to be robust in the presence of outliers and corrupted data, as well as being "aware" of its limits, i.e. the system should maintain and provide an uncertainty estimate over its own predictions. These complex demands are among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology into every day’s applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. First we provide a comprehensive review of resource-efficiency in deep neural networks with focus on techniques for model size reduction, compression and reduced precision. These techniques can be applied during training or as post-processing and are widely used to reduce both computational complexity and memory footprint. As most (practical) neural networks are limited in their ways to treat uncertainty, we contrast them with probabilistic graphical models, which readily serve these desiderata by means of probabilistic inference. In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Improving efficiency in convolutional neural network with multilinear filters

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Tran, Dat Thanh Iosifidis, Alexandros Gabbouj, Moncef Laboratory of Signal Processing Tampere University of Technology Tampere Finland Department of Engineering Electrical and Computer Engineering Aarhus University Aarhus Denmark

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require billions of floating point operations. Several works have been developed to compress a pre-trained deep network to reduce memory footprint and, possibly, computation. Instead of compressing a pre-trained network, in this work, we propose a generic neural network layer structure employing multilinear projection as the primary feature extractor. The proposed architecture requires several times less memory as compared to the traditional Convolutional Neural Networks (CNN), while inherits the similar design principles of a CNN. In addition, the proposed architecture is equipped with two computation schemes that enable computation reduction or scalability. Experimental results show the effectiveness of our compact projection that outperforms traditional CNN, while requiring far fewer parameters. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

A Subpixel Target Detection Approach to Hyperspectral Image Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2017年第9期55卷 5093-5114页

作者： Xue, Bai Yu, Chunyan Wang, Yulei Song, Meiping Li, Sen Wang, Lin Chen, Hsian-Min Chang, Chein-I Center for Hyperspectral Imaging in Remote Sensing Information and Technology College Dalian Maritime University Dalian China Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County BaltimoreMD21250 United States Key Laboratory of Spectral Imaging Technology Chinese Academy of Sciences Xi'an China State Key Laboratory of Integrated Services Networks Xi'an China School of Physics and Optoelectronic Engineering Xidian University Xi'an China Department of Medical Research Taichung Veterans General Hospital Taichung Taiwan Department of Computer Science and Information Management Providence University Taichung02912 Taiwan

Hyperspectral image classification faces various levels of difficulty due to the use of different types of hyperspectral image data. Recently, spectral-spatial approaches have been developed by jointly taking care of spectral and spatial information. This paper presents a completely different approach from a subpixel target detection view point. It implements four stage processes, a preprocessing stage, which uses band selection (BS) and nonlinear band expansion, referred to as BS-then-nonlinear expansion (BSNE), a detection stage, which implements constrained energy minimization (CEM) to produce subpixel target maps, and an iterative stage, which develops an iterative CEM (ICEM) by applying Gaussian filters to capture spatial information, and then feeding the Gaussian-filtered CEM-detection maps back to BSNE band images to reprocess CEM in an iterative manner. Finally, in the last stage Otsu's method is applied to converting ICEM-detected real-valued maps to discrete values for classification. The entire process is called BSNE-ICEM. Experimental results demonstrate BSNE-ICEM, which has advantages over support vector machine-based approaches in many aspects, such as easy implementation, fewer parameters to be used, and better false classification and precision rates. © 1980-2012 IEEE.

关键词： Support vector machines

Comments on "Design of fractional-order variants of complex LMS and NLMS algorithms for adaptive channel equalization"

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Khan, Shujaat Wahab, Abdul Naseem, Imran Moinuddin, Muhammad Bio-imaging and Signal Processing Laboratory Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology 291 Daehak-ro Daejeon Yuseong-gu34141 Korea Republic of Department of Mathematics University of Education Attock Campus43600 Pakistan School of Electrical Electronic and Computer Engineering University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia College of Engineering Karachi Institute of Economics and Technology Korangi Creek Karachi75190 Pakistan King Abdulaziz University Jeddah Saudi Arabia Electrical and Computer Engineering Department King Abdulaziz University Jeddah Saudi Arabia

The purpose of this note is to highlight some critical flaws in recently proposed fractional-order variants of complex least mean square (CLMS) and normalized least mean square (NLMS) algorithms in "Design of Fractional-order Variants of Complex LMS and Normalized LMS Algorithms for Adaptive Channel Equalization" [Non-linear Dyn. 88(2), 839-858 (2017)]. It is substantiated that these algorithms do not always converge whereas they have no advantage over the CLMS and NLMS algorithms whenever they converge. Our claims are based on analytical reasoning supported by simulations. Copyright © 2018, The Authors. All rights reserved.

关键词： Equalizers

Edgy salient local binary patterns in inter-plane relationship for image retrieval in Diabetic Retinopathy

学校读者我要写书评

暂无评论

Procedia computer Science 2017年 115卷 440-447页

作者： Gajanan M. Galshetwar Laxman M. Waghmare Anil B. Gonde Subrahmanyam Murala Center of Excellence in Signal and Image Processing (COESIP) Department of ECE SGGSIET Nanded Maharashtra 431606 India Computer Vision and Pattern Recognition Laboratory Department of Electrical Engineering IIT Ropar Rupnagar 140001 India

In this paper, a novel approach for content based image retrieval (CBIR) in diabetic retinopathy (DR) is proposed. The concept of salient point selection and inter-plane relationship technique is used. Salient points are selected from edgy image and later using inter-planer relationship, Local Binary Patterns (LBPs) are calculated using the salient point as a center pixel. Our approach enhanced the results as we used color features in combination with LBP features. Experimentation is carried out on MESSIDOR database of 1200 retinal images, proposed approach has average precision of 57.82% as compared to the earlier approach whose average precision is 53.70%.

关键词： Content-Based image retrieval (CBIR) Diabetic Retinopathy (DR) Edgy Salient points Local Binary Patterns (LBPs)

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

学校读者我要写书评

暂无评论

Nature methods 2024年第10期21卷 1959页

作者： Linus Manubens-Gil Zhi Zhou Hanbo Chen Arvind Ramanathan Xiaoxiao Liu Yufeng Liu Alessandro Bria Todd Gillette Zongcai Ruan Jian Yang Miroslav Radojević Ting Zhao Li Cheng Lei Qu Siqi Liu Kristofer E Bouchard Lin Gu Weidong Cai Shuiwang Ji Badrinath Roysam Ching-Wei Wang Hongchuan Yu Amos Sironi Daniel Maxim Iascone Jie Zhou Erhan Bas Eduardo Conde-Sousa Paulo Aguiar Xiang Li Yujie Li Sumit Nanda Yuan Wang Leila Muresan Pascal Fua Bing Ye Hai-Yan He Jochen F Staiger Manuel Peter Daniel N Cox Michel Simonneau Marcel Oberlaender Gregory Jefferis Kei Ito Paloma Gonzalez-Bellido Jinhyun Kim Edwin Rubel Hollis T Cline Hongkui Zeng Aljoscha Nern Ann-Shyn Chiang Jianhua Yao Jane Roskams Rick Livesey Janine Stevens Tianming Liu Chinh Dang Yike Guo Ning Zhong Georgia Tourassi Sean Hill Michael Hawrylycz Christof Koch Erik Meijering Giorgio A Ascoli Hanchuan Peng Institute for Brain and Intelligence Southeast University Nanjing China. Microsoft Corporation Redmond WA USA. Tencent AI Lab Bellevue WA USA. Computing Environment and Life Sciences Directorate Argonne National Laboratory Lemont IL USA. Kaya Medical Seattle WA USA. University of Cassino and Southern Lazio Cassino Italy. Center for Neural Informatics Structures and Plasticity Krasnow Institute for Advanced Study George Mason University Fairfax VA USA. Faculty of Information Technology Beijing University of Technology Beijing China. Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing China. Nuctech Netherlands Rotterdam the Netherlands. Janelia Research Campus Howard Hughes Medical Institute Ashburn VA USA. Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada. Ministry of Education Key Laboratory of Intelligent Computation and Signal Processing Anhui University Hefei China. Paige AI New York NY USA. Scientific Data Division and Biological Systems and Engineering Division Lawrence Berkeley National Lab Berkeley CA USA. Helen Wills Neuroscience Institute and Redwood Center for Theoretical Neuroscience UC Berkeley Berkeley CA USA. RIKEN AIP Tokyo Japan. Research Center for Advanced Science and Technology (RCAST) The University of Tokyo Tokyo Japan. School of Computer Science University of Sydney Sydney New South Wales Australia. Texas A&M University College Station TX USA. Cullen College of Engineering University of Houston Houston TX USA. Graduate Institute of Biomedical Engineering National Taiwan University of Science and Technology Taipei Taiwan. National Centre for Computer Animation Bournemouth University Poole UK. PROPHESEE Paris France. Department of Neuroscience Columbia University New York NY USA. Mortimer B. Zuckerman Mind Brain Behavior Institute Columbia University New York NY USA. Department of Computer Science Northern Illinois Universit

Tensor representation in high-frequency financial data for price change prediction

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Tran, Dat Thanh Magris, Martin Kanniainen, Juho Gabbouj, Moncef Iosifidis, Alexandros Laboratory of Signal Processing Tampere University of Technology Tampere Finland Laboratory of Industrial and Information Management Tampere University of Technology Tampere Finland Department of Engineering Electrical & Computer Engineering Aarhus University Aarhus Denmark

Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high-frequency traders. In order to take advantage of the rapid, subtle movement of assets in High-Frequency Trading (HFT), an automatic algorithm to analyze and detect patterns of price change based on transaction records must be available. The multichannel, time-series representation of financial data naturally suggests tensor-based learning algorithms. In this work, we investigate the effectiveness of two multilinear methods for the mid-price prediction problem against other existing methods. The experiments in a large-scale dataset which contains more than 4 million limit orders show that by utilizing tensor representation, multilinear models outperform vector-based approaches and other competing ones. Copyright © 2017, The Authors. All rights reserved.

关键词： Tensors

Temporal attention augmented bilinear network for financial time-series data analysis

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Tran, Dat Thanh Iosifidis, Alexandros Kanniainen, Juho Gabbouj, Moncef Laboratory of Signal Processing Tampere University of Technology Tampere Finland Department of Engineering Electrical & Computer Engineering Aarhus University Aarhus Denmark Laboratory of Industrial and Information Management Tampere University of Technology Tampere Finland

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale Limit Order Book (LOB) dataset show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations. Copyright © 2017, The Authors. All rights reserved.

关键词： Time series

Tensor representation in high-frequency financial data for price change prediction

学校读者我要写书评

暂无评论

Tensor representation in high-frequency financial data for p...

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Dat Thanh Tran Martin Magris Juho Kanniainen Moncef Gabbouj Alexandros Iosifidis Laboratory of Signal Processing Tampere University of Technology Tampere Finland Laboratory of Industrial and Information Management Tampere University of Technology Tampere Finland Department of Engineering Electrical & Computer Engineering Aarhus University Aarhus Denmark

Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high frequency traders. In order to take advantage of the rapid, subtle movement of assets in High Frequency Trading (HFT), an automatic algorithm to analyze and detect patterns of price change based on transaction records must be available. The multichannel, time-series representation of financial data naturally suggests tensor-based learning algorithms. In this work, we investigate the effectiveness of two multilinear methods for the mid-price prediction problem against other existing methods. The experiments in a large scale dataset which contains more than 4 millions limit orders show that by utilizing tensor representation, multilinear models outperform vector-based approaches and other competing ones.

关键词： Tensile stress Mathematical model Recurrent neural networks Feature extraction Heuristic algorithms Prediction algorithms