检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Vargas-Solar, Genoveva CNRS Univ Lyon INSA Lyon UCBL LIRIS UMR5205 VilleurbanneF-69622 France

Datification, introduced by Kenneth Cukier and Viktor Mayer-Schönberger (Biltgen and Ryan (2016)), refers to the controversial and barbarian possibility of generating digital twins of every being and thing on Earth thanks to sensors, data and algorithms. Digital colonisation and neoliberal processes in a datified world are beyond the limits of the material world, beyond time and geographical location. Big Data and artificial intelligence combined have led to data science representing the scientific and"mechanical" materialisation of datification. Scholars like N. Couldry and U. Mejíías (Couldry and Mejias (2021a)), P. Ricaurte (Ricaurte (2019)) and S.U. Noble (Noble (2018)) define this data-centred phenomenon as a form of data colonialism 1. Through its problematic epistemic basis, data science steps into human life systematically, massively and without being questioned. Global north and south countries see in this project the opportunity to observe, control and tune lives, beliefs, and thoughts without people even being aware. No place is unreachable, and people are progressively formatted to believe and organise their aims towards the ideals of savage capitalism"values" injected by the digital hegemony. There is ongoing colonisation of the minds and expectations with temporalities that see in datafication and the"opportunities" it opens as the ultimate evolution of humanity. The impact of datification and algorithms re-creating and reproducing colonial violence promises to be increasingly devastating for people in the margins, women and young children very often. Scholars like M. Lampard and S.L. Star (Lampland and Star (2009)) have problematised the quantification of social phenomena and people’s behaviour showing how hegemonic thinking biases the choice of variables representing categories and how they are"engineered" to be processed by machine learning algorithms and numerical methods. For example, algorithms adopting supervised learning methods 2 use bi-gender

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design

arXiv

引用

arXiv 2022年

作者： Feng, Lang Liu, Wenjian Guo, Chuliang Tang, Ke Zhuo, Cheng Wang, Zhongfeng Nanjing University 163 Xianlin Road Nanjing210023 China Zhejiang University 866 Yuhangtang Road Hangzhou310058 China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province China

With the popularity of deep learning, the hardware implementation platform of deep learning has received increasing interest. Unlike the general purpose devices, e.g., CPU, or GPU, where the deep learning algorithms are executed at the software level, neural network hardware accelerators directly execute the algorithms to achieve higher both energy efficiency and performance improvements. However, as the deep learning algorithms evolve frequently, the engineering effort and cost of designing the hardware accelerators are greatly increased. To improve the design quality while saving the cost, design automation for neural network accelerators was proposed, where design space exploration algorithms are used to automatically search the optimized accelerator design within a design space. Nevertheless, the increasing complexity of the neural network accelerators brings the increasing dimensions to the design space. As a result, the previous design space exploration algorithms are no longer effective enough to find an optimized design. In this work, we propose a neural network accelerator design automation framework named GANDSE, where we rethink the problem of design space exploration, and propose a novel approach based on the generative adversarial network (GAN) to support an optimized exploration for high dimension large design space. The experiments show that GANDSE is able to find the more optimized designs in negligible time compared with approaches including multilayer perceptron and deep reinforcement learning. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal Network Reconfiguration for Real Power Losses Reduction using Sparrow Search Algorithm

TechRxiv

引用

TechRxiv 2022年

作者： Mtonga, Thomson P.M. Kaberere, Keren K. Irungu, George K. The Department of Civil Aviation Ministry of Transport and Public Infrastructure Lilongwe Malawi Nairobi Kenya

Optimal network reconfiguration helps with the reduction of total real power losses and the improvement of bus voltages. Several optimal network reconfiguration approaches are available in literature. However, as shown by a very recent study on the IEEE 33-bus radial distribution system, these approaches fail to attain the least total real power losses. Despite that, the recent study did not consider multiple test systems and load variations. Consequently, this article addresses those unexplored areas by introducing an optimal network reconfiguration approach that minimizes the total real power losses in the standard IEEE 33- and 69-bus radial distribution systems under nominal (100%) and heavy (160%) load conditions. The developed approach, which is based on Sparrow Search Algorithm, intelligently searches for the optimum tie and sectionalizing branches that have to be switched on and off, respectively, in order to minimize the systems’ total real power losses. The search for the optimum tie and sectionalizing branches is performed in the permutations of loops created by the radial distribution systems’ tie and sectionalizing branches. For the considered two test systems, the developed approach gave the least total real power losses and the best bus voltages than the referenced approaches. © 2022, CC BY.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learned Fair Representations using Dampening and Stacking

arXiv

引用

arXiv 2022年

作者： Knobbout, Max Just Eat *** Netherlands

MSC Codes 68T07As more decisions in our daily life become automated, the need to have machine learning algorithms that make fair decisions increases. In fair representation learning we are tasked with finding a suitable representation of the data in which a sensitive variable is censored. Recent work aims to learn fair representations through adversarial learning. This paper builds upon this work by introducing a novel algorithm which uses dampening and stacking to learn adversarial fair representations. Results show that that our algorithm improves upon earlier work in both censoring and reconstruction. © 2022, CC BY.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Fusion by Meta-Initialization

arXiv

引用

arXiv 2022年

作者： Jackson, Matthew T. Malik, Shreshth A. Matthews, Michael T. Mohamed-Ahmed, Yousuf Department of Engineering Science University of Oxford United Kingdom Department of Computer Science University College London United Kingdom

When experience is scarce, models may have insufficient information to adapt to a new task. In this case, auxiliary information—such as a textual description of the task—can enable improved task inference and adaptation. In this work, we propose an extension to the Model-Agnostic Meta-learning algorithm (MAML), which allows the model to adapt using auxiliary information as well as task experience. Our method, Fusion by Meta-Initialization (FuMI), conditions the model initialization on auxiliary information using a hypernetwork, rather than learning a single, task-agnostic initialization. Furthermore, motivated by the shortcomings of existing multi-modal few-shot learning benchmarks, we constructed iNat-Anim—a large-scale image classification dataset with succinct and visually pertinent textual class descriptions. On iNat-Anim, FuMI significantly outperforms uni-modal baselines such as MAML in the few-shot regime. © 2022, CC BY.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Stress-Testing Point Cloud Registration on Automotive LiDAR

arXiv

引用

arXiv 2022年

作者： Drory, Amnon Avidan, Shai Giryes, Raja Tel-Aviv University

Rigid Point Cloud Registration (PCR) algorithms aim to estimate the 6-DOF relative motion between two point clouds, which is important in various fields, including autonomous driving. Recent years have seen a significant improvement in global PCR algorithms, i.e. algorithms that can handle a large relative motion. This has been demonstrated in various scenarios, including indoor scenes, but has only been minimally tested in the Automotive setting, where point clouds are produced by vehicle-mounted LiDAR sensors. In this work, we aim to answer questions that are important for automotive applications, including: which of the new algorithms is the most accurate, and which is fastest? How transferable are deep-learning approaches, e.g. what happens when you train a network with data from Boston, and run it in a vehicle in Singapore? How small can the overlap between point clouds be before the algorithms start to deteriorate? To what extent are the algorithms rotation invariant? Our results are at times surprising. When comparing robust parameter estimation methods for registration, we find that the fastest and most accurate is not one of the newest approaches. Instead, it is a modern variant of the well known RANSAC technique. We also suggest a new outlier filtering method, Grid-Prioritized Filtering (GPF), to further improve it. An additional contribution of this work is an algorithm for selecting challenging sets of frame-pairs from automotive LiDAR datasets. This enables meaningful benchmarking in the Automotive LiDAR setting, and can also improve training for learning algorithms. We share our code and registration sets.1 © 2022, CC BY-NC-SA.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Spectrum-BERT: Pre-training of Deep Bidirectional Transformers for Spectral Classification of Chinese Liquors

arXiv

引用

arXiv 2022年

作者： Wang, Yansong Sun, Yundong Fu, Yansheng Zhu, Dongjie Tian, Zhaoshuo The School of Computer Science and Technology Harbin Institute of Technology at Weihai Weihai264209 China The Department of Electronic Science and Technology Harbin Institute of Technology Harbin150001 China The Institute of Marine Optoelectronic Equipment Harbin Institute of Technology at Weihai Weihai264209 China

The frequent occurrence of Chinese liquor counterfeiting incidents has disturbed market operation orders and even seriously damaged consumers’ health. Spectral detection technology, as a non-invasive method for rapid detection of substances, combined with deep learning algorithms, has been widely used in food detection. However, in real scenarios, acquiring and labeling spectral data is an extremely labor-intensive task, which makes it impossible to provide enough high-quality data for training efficient supervised deep learning models. To better leverage limited samples, we apply"pre-training & fine-tuning" paradigm to the field of spectral detection for the first time and propose a pre-training method of deep bidirectional transformers for spectral classification of Chinese liquors, abbreviated as Spectrum-BERT. Specifically, first, to retain the model’s sensitivity to the characteristic peak position and local information of the spectral curve, we innovatively partition the curve into multiple blocks and obtain the embeddings of different blocks, as the feature input for the next calculation. Second, in the pre-training stage, we elaborately design two pre-training tasks, Next Curve Prediction (NCP) and Masked Curve Model (MCM), so that the model can effectively utilize unlabeled samples to capture the potential knowledge of spectral data, breaking the restrictions of the insufficient labeled samples, and improving the applicability and performance of the model in practical scenarios. Finally, we conduct a large number of experiments on the real liquor spectral dataset. In the comparative experiments, the proposed Spectrum-BERT significantly outperforms the baselines in multiple metrics and this advantage is more significant on the imbalanced dataset. Moreover, in the parameter sensitivity experiment, we also analyze the model performance under different parameter settings, to provide a reference for subsequent research. Copyright © 2022, The Authors. All rights

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Non-Crossing Quantiles through the Partial Derivative

arXiv

引用

arXiv 2022年

作者： Guillaumes, Axel Brando Gimeno, Joan Rodríguez-Serrano, José A. Vitrià, Jordi Spain Spain

Quantile Regression (QR) provides a way to approximate a single conditional quantile. To have a more informative description of the conditional distribution, QR can be merged with deep learning techniques to simultaneously estimate multiple quantiles. However, the minimisation of the QR-loss function does not guarantee non-crossing quantiles, which affects the validity of such predictions and introduces a critical issue in certain scenarios. In this article, we propose a generic deep learning algorithm for predicting an arbitrary number of quantiles that ensures the quantile monotonicity constraint up to the machine precision and maintains its modelling performance with respect to alternative models. The presented method is evaluated over several real-world datasets obtaining state-of-the-art results as well as showing that it scales to large-size data sets. © 2022, CC BY-SA.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

THE TROPICAL GEOMETRY OF CAUSAL INFERENCE FOR EXTREMES

arXiv

引用

arXiv 2022年

作者： Tran, NGOC Mai Department of Mathematics The University of Texas Austin United States

Extreme value statistics is the max analogue of classical statistics, while tropical geometry is the max analogue of classical geometry. In this paper, we review recent work where insights from tropical geometry were used to develop new, efficient learning algorithms with leading performance on benchmark datasets in extreme value statistics. We give intuition, backed by performances on benchmark datasets, for why and when causal inference for extremes should be employed over classical methods. Finally, we list some open problems at the intersection of causal inference, tropical geometry and deep learning. © 2022, CC BY.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

AGREE TO DISAGREE: DIVERSITY THROUGH DISAGREEMENT FOR BETTER TRANSFERABILITY

arXiv

引用

arXiv 2022年

作者： Pagliardini, Matteo Jaggi, Martin Fleuret, François Karimireddy, Sai Praneeth EPFL Switzerland EPFL UC Berkeley United States

Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i) favoring the learning of simpler but spurious features - present in the training data but absent from the test data - and (ii) by only leveraging a small subset of predictive features. Such an effect is especially magnified when the test distribution does not exactly match the train distribution-referred to as the Out of Distribution (OOD) generalization problem. However, given only the training data, it is not always possible to apriori assess if a given feature is spurious or transferable. Instead, we advocate for learning an ensemble of models which capture a diverse set of predictive features. Towards this, we propose a new algorithm D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data, but disagreement on the OOD data. We show how D-BAT naturally emerges from the notion of generalized discrepancy, as well as demonstrate in multiple experiments how the proposed method can mitigate shortcut-learning, enhance uncertainty and OOD detection, as well as improve transferability. © 2022, CC BY.

关键词： learning algorithms

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：