检索结果-内蒙古大学图书馆

Quantum optical experiments modeled by long short-term memory

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Adler, Thomas Erhard, Manuel Krenn, Mario Brandstetter, Johannes Kofler, Johannes Hochreiter, Sepp Institute for Machine Learning LIT AI Lab Johannes Kepler University Linz Linz Austria Institute for Quantum Optics Quantum Information Austrian Academy of Sciences Vienna Center for Quantum Science & Technology University of Vienna Vienna Austria Dept. of Chemistry Dept. of Computer Science University of Toronto Vector Institute for Artificial Intelligence Toronto Canada

We demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a large number of entangled quantum levels. Given such a multiparticle high-dimensional quantum state, it is usually impossible to reconstruct an experimental setup that produces it. To search for interesting experiments, one thus has to randomly create millions of setups on a computer and calculate the respective output states. In this work, we show that machine learning models can provide significant improvement over random search. We demonstrate that a long short-term memory (LSTM) neural network can successfully learn to model quantum experiments by correctly predicting output state characteristics for given setups without the necessity of computing the states themselves. This approach not only allows for faster search but is also an essential step towards automated design of multiparticle high-dimensional quantum experiments using generative machine learning models. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

Credit Risk Analysis Using machine learning Techniques

学校读者我要写书评

暂无评论

Credit Risk Analysis Using Machine Learning Techniques

Information Processing (ICINPRO), International Conference on

作者： S.J. Shiv Srinivasa Murthy Krishnaprasad Challuru Dept. of Computer Science PES University Bangalore India Artificaial Intelligince & Machine Learning Consultant Bangalore India

ISBN: (数字)9781538677964

ISBN: (纸本)9781538677971

Financial institutes like banks spend significant effort in identifying credit-worthy consumers for lending. In this paper, we study the performance of various classification algorithms applied to a real-life data set for consumer lending. Various types of classifiers (logistic regression, random forest, neural networks) are evaluated and their performance compared. The data set is first pre-processed to select best attributes and to remove outliers for classification. The performance is assessed using various metrics including the classification accuracy, precision, recall and specificity. It is found that logistic regression yields very good performance. By varying the cut off ratio in random forest it is possible to trade off precision and recall to filter those consumers who are credit-worth.

关键词： Support vector machines Neural networks Classification algorithms Logistics machine learning Genetic algorithms Probability

Tracking all members of a honey bee colony over their lifetime using learned models of correspondence

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Boenisch, Franziska Rosemann, Benjamin Wild, Benjamin Wario, Fernando Dormagen, David Landgraf, Tim Dahlem Center of Machine Learning and Robotics Dept. Mathematics and Computer Science Freie Universität Berlin Berlin Germany

Computational approaches to the analysis of collective behavior in social insects increasingly rely on motion paths as an intermediate data layer from which one can infer individual behaviors or social interactions. Honey bees are a popular model for learning and memory. Previous experience has been shown to affect and modulate future social interactions. So far, no lifetime history observations have been reported for all bees of a colony. In a previous work we introduced a recording setup customized to track up to 4000 marked bees over several weeks. Due to detection and decoding errors of the bee markers, linking the correct correspondences through time is non-trivial. In this contribution we present an in-dept. description of the underlying multi-step algorithm which produces motion paths, and also improves the marker decoding accuracy significantly. The proposed solution employs two classifiers to predict the correspondence of two consecutive detections in the first step, and two tracklets in the second. We automatically tracked ∼2000 marked honey bees over 10 weeks with inexpensive recording hardware using markers without any error correction bits. We found that the proposed two-step tracking reduced incorrect ID decodings from initially ∼13% to around 2% post-tracking. Alongside this paper, we publish the first trajectory dataset for all bees in a colony, extracted from ∼3 million images covering three days. We invite researchers to join the collective scientific effort to investigate this intriguing animal system. All components of our system are open-source. Copyright © 2018, The Authors. All rights reserved.

关键词： Decoding

APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions

学校读者我要写书评

暂无评论

APPINITE: A Multi-Modal Interface for Specifying Data Descri...

IEEE Symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Toby Jia-Jun Li Igor Labutov Xiaohan Nancy Li Xiaoyi Zhang Wenze Shi Wanling Ding Tom M. Mitchell Brad A. Myers HCI Institute Machine Learning Dept. Computer Science Dept. Computer Science &Engineering University of Washington Seattle WA USA Information Systems Dept. Carnegie Mellon University Pittsburgh PA USA

A key challenge for generalizing programming-by-demonstration (PBD) scripts is the data description problem - when a user demonstrates performing an action, the system needs to determine features for describing this action and the target object in a way that can reflect the user's intention for the action. However, prior approaches for creating data descriptions in PBD systems have problems with usability, applicability, feasibility, transparency and/or user control. Our APPINITE system introduces a multimodal interface with which users can specify data descriptions verbally using natural language instructions. APPINITE guides users to describe their intentions for the demonstrated actions through mixed-initiative conversations. APPINITE constructs data descriptions for these actions from the natural language instructions. Our evaluation showed that APPINITE is easy-to-use and effective in creating scripts for tasks that would otherwise be difficult to create with prior PBD systems, due to ambiguous data descriptions in demonstrations on GUIs.

关键词： Task analysis Natural languages Programming Graphical user interfaces Semantics Automation Visualization

ProSper - A python library for probabilistic sparse coding with non-standard priors and superpositions

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Exarchakis, Georgios Bornschein, Jörg Sheikh, Abdul-Saboor Dai, Zhenwen Henniges, Marc Drefs, Jakob Lücke, Jörg Sorbonne Université INSERM CNRS Institut de la Vision Paris France FIAS Goethe-Universität Frankfurt am Main Germany Zalando Research Berlin Germany Dept of Computer Science University of Sheffield United Kingdom d-fine GmbH Frankfurt Germany Machine Learning Division C. v. Ossietzky Universität Oldenburg Germany

ProSper is a python library containing probabilistic algorithms to learn dictionaries. Given a set of data points, the implemented algorithms seek to learn the elementary components that have generated the data. The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard L1 sparse coding. The implemented algorithms are especially well-suited in cases when data consist of components that combine non-linearly and/or for data requiring flexible prior distributions. Furthermore, the implemented algorithms go beyond standard approaches by inferring prior and noise parameters of the data, and they provide rich a-posteriori approximations for inference. The library is designed to be extendable and it currently includes: Binary Sparse Coding (BSC), Ternary Sparse Coding (TSC), Discrete Sparse Coding (DSC), Maximal Causes Analysis (MCA), Maximum Magnitude Causes Analysis (MMCA), and Gaussian Sparse Coding (GSC, a recent spike-and-slab sparse coding approach). The algorithms are scalable due to a combination of variational approximations and parallelization. Implementations of all algorithms allow for parallel execution on multiple CPUs and multiple machines for medium to large-scale applications. Typical large-scale runs of the algorithms can use hundreds of CPUs to learn hundreds of dictionary elements from data with tens of millions of floating-point numbers such that models with several hundred thousand parameters can be optimized. The library is designed to have minimal dependencies and to be easy to use. It targets users of dictionary learning algorithms and machine learning researchers. Copyright © 2019, The Authors. All rights reserved.

关键词： Python

Spatial 3D Matern priors for fast Whole-Brain fMRI analysis

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Siden, Per Lindgren, Finn Bolinz, David Eklund, Anders Villani, Mattias Division of Statistics and Machine Learning Dept. of Computer and Information Science Linkoping University LinkopingSE-58183 School of Mathematics University of Edinburgh Peter Guthrie Tait Road EdinburghEH93FD United Kingdom Division of Applied Mathematics and Statistics Dept. of Mathematical Sciences Chalmers and University of Gothenburg GoteborgSE-41296 Division of Medical Informatics Dept. of Biomedical Engineering Center for Medical Image Science and Visualization Linkoping University LinkopingSE-58183 Department of Statistics Stockholm University StockholmSE-10691 Sweden

Bayesian whole-brain functional magnetic resonance imaging (fMRI) analysis with three-dimensional spatial smoothing priors have been shown to produce state-of-the-art activity maps without pre-smoothing the data. The proposed inference algorithms are computationally demanding however, and the proposed spatial priors have several less appealing properties, such as being improper and having infinite spatial range. Our paper proposes a statistical inference framework for functional magnetic resonance imaging (fMRI) analysis based on the class of Matern covariance functions. The framework uses the Gaussian Markov random field (GMRF) representation of Matern fields via the stochastic partial difierential equation (SPDE) approach of Lindgren et al. (2011). This allows for more exible and interpretable spatial priors, while maintaining the sparsity required for fast inference in the high-dimensional whole-brain setting. We develop an accelerated stochastic gradient descent (SGD) optimization algorithm for empirical Bayes (EB) inference of the spatial hyperparameters. Conditional on the inferred hyperparameters, we make a fully Bayesian treatment of the main parameters of interest, that is, the brain activity coeficients. We apply the Matern prior to both experimental and simulated task-fMRI data and clearly demonstrate that this is a more reasonable choice than the previously used priors, by using prior simulation, cross validation and visual inspection of the resulting activation maps. Additionally, to illustrate the potential of the SPDE formulation, we derive an anisotropic version of the Matern 3D prior. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Scene reconstruction from a single dept. image using 3D CNN 2017

学校读者我要写书评

暂无评论

Scene reconstruction from a single depth image using 3D CNN

2017 International Conference on Computational Biology and Bioinformatics, ICCBB 2017

作者： Palla, Alessandro Moloney, David Fanucci, Luca Computer Vision and Machine Learing Group Movidius Intel United States Dept. of Information Engineering University of Pisa Italy

ISBN: (纸本)9781450353229

Scene reconstruction from multiple viewpoints are not always possible and rather it represents a small minority of the potential applications, from robotic manipulators to drones, autonomous vehicles etc. To overcome those limitations, we propose a fully convolutional 3D neural network capable of reconstructing a full scene from a single dept. image by creating a 3D representation of it and automatically filling holes and inserting hidden elements. Our algorithm was evaluated on a real word dataset of tabletop scenes acquired using a Kinect and processed using KinectFusion software in order to obtain ground truth for network training and evaluation. Extensive measurements show that our deep neural network architecture outperforms the previous state of the art in terms of both precision and recall for the scene reconstruction task.

关键词： Image reconstruction

Higher-level Knowledge, Rational and Social Levels Constraints of the Common Model of the Mind

学校读者我要写书评

暂无评论

Procedia computer Science 2018年 145卷 757-764页

作者： Antonio Lieto William G. Kennedy Christian Lebiere Oscar J. Romero Niels Taatgen Robert L. West University of Turin Dept. of Computer Science and ICAR-CNR (Palermo) Italy Center for Social Complexity George Mason University USA Carnegie Mellon University Dept. of Psychology USA Carnegie Mellon University Dept. of Machine Learning USA AI and Cognitive Engineering Institute University of Groningen The Netherlands Institute of Cognitive Science Carleton University Canada

We present the input to the discussion about the computational framework known as Common Model of Cognition (CMC) from the working group dealing with the knowledge/rational/social levels. In particular, we present a l... 详细信息

关键词： Unified Cognitive Architectures Computational Models of Cognition Common Model of the Mind Cognitive Constraints Knowledge Level Rational Level Social Level

End-to-end, single-stream temporal action detection in untrimmed videos 28

学校读者我要写书评

暂无评论

End-to-end, single-stream temporal action detection in untri...

28th British machine vision Conference, BMVC 2017

作者： Buch, Shyamal Escorcia, Victor Ghanem, Bernard Fei-Fei, Li Niebles, Juan Carlos Stanford Vision and Learning Lab. Dept. of Computer Science Stanford University United States Image and Video Understanding Lab. Visual Computing Center KAUST Saudi Arabia

ISBN: (纸本)190172560X

In this work, we present a new intuitive, end-to-end approach for temporal action detection in untrimmed videos. We introduce our new architecture for Single-Stream Temporal Action Detection (SS-TAD), which effectively integrates joint action detection with its semantic sub-tasks in a single unifying end-to-end framework. We develop a method for training our deep recurrent architecture based on enforcing semantic constraints on intermediate modules that are gradually relaxed as learning progresses. We find that such a dynamic learning scheme enables SS-TAD to achieve higher overall detection performance, with fewer training epochs. By design, our single-pass network is very efficient and can operate at 701 frames per second, while simultaneously outperforming the state-of-the-art methods for temporal action detection on THUMOS’14. © 2017. The copyright of this document resides with its authors.

关键词： Semantics