检索结果-内蒙古大学图书馆

On limitations of learning algorithms in competitive environments

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Klimenko, Alexander Y. Klimenko, Dimitri A. SoMME The University of Queensland QLD4072 Australia

We discuss conceptual limitations of generic learning algorithms pursuing adversarial goals in competitive environments, and prove that they are subject to limitations that are analogous to the constraints on knowledge imposed by the famous theorems of Gödel and Turing. These limitations are shown to be related to intransitivity, which is commonly present in competitive environments. Copyright © 2020, The Authors. All rights reserved.

关键词： learning algorithms

RealMix: Towards realistic semi-supervised deep learning algorithms

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Nair, Varun Alonso, Javier Fuentes Beltramelli, Tony Duke University DurhamNC United States Uizard Technologies Copenhagen Denmark

Semi-Supervised learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior SSL algorithms suffer from. In particular, poor performance when unlabeled and labeled data distributions differ. To address these observations, we develop RealMix, which achieves state-of-the-art results on standard benchmark datasets across different labeled and unlabeled set sizes while overcoming the aforementioned challenges. Notably, RealMix achieves an error rate of 9.79% on CIFAR10 with 250 labels, and is the only SSL method tested able to surpass baseline performance when there is significant mismatch in the labeled and unlabeled data distributions. RealMix demonstrates how SSL can be used in real world situations with limited access to both data and compute and guides further research in SSL with practical applicability in mind. Copyright © 2019, The Authors. All rights reserved.

关键词： learning algorithms

EVALUATION AND COMPARISON OF FEDERATED learning algorithms FOR HUMAN ACTIVITY RECOGNITION ON SMARTPHONES

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ek, Sannara Portet, François Lalanda, Philippe Vega, German University Grenoble Alpes LIG GrenobleF-38000 France

Pervasive computing promotes the integration of smart devices in our living spaces to develop services providing assistance to people. Such smart devices are increasingly relying on cloud-based Machine learning, which raises questions in terms of security (data privacy), reliance (latency), and communication costs. In this context, Federated learning (FL) has been introduced as a new machine learning paradigm enhancing the use of local devices. At the server level, FL aggregates models learned locally on distributed clients to obtain a more general model. In this way, no private data is sent over the network, and the communication cost is reduced. Unfortunately, however, the most popular federated learning algorithms have been shown not to be adapted to some highly heterogeneous pervasive computing environments. In this paper, we propose a new FL algorithm, termed FedDist, which can modify models (here, deep neural network) during training by identifying dissimilarities between neurons among the clients. This permits to account for clients' specificity without impairing generalization. FedDist evaluated with three state-of-the-art federated learning algorithms on three large heterogeneous mobile Human Activity Recognition datasets. Results have shown the ability of FedDist to adapt to heterogeneous data and the capability of FL to deal with asynchronous situations. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Multivariate Systemic Risk Measures and Computation by Deep learning algorithms

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Doldi, Alessandro Feng, Yichen Fouque, Jean-Pierre Frittelli, Marco Università degli Studi di Milano Italy University of California Santa Barbara United States

In this work we propose deep learning-based algorithms for the computation of systemic shortfall risk measures defined via multivariate utility functions. We discuss the key related theoretical aspects, with a particular focus on the fairness properties of primal optima and associated risk allocations. The algorithms we provide allow for learning primal optimizers, optima for the dual representation and corresponding fair risk allocations. We test our algorithms by comparison to a benchmark model, based on a paired exponential utility function, for which we can provide explicit formulas. We also show evidence of convergence in a case for which explicit formulas are not *** Codes 91B05, 68T07 © 2023, CC BY.

关键词： learning algorithms

Investigating the validity of structure learning algorithms in identifying risk factors for intervention in patients with diabetes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zahoor, Sheresh Constantinou, Anthony C. Curtis, Tim M. Hasanuzzaman, Mohammed Munster Technological University Rossa Ave Bishopstown CorkT12 P928 Ireland LondonE1 4NS United Kingdom Queen’s University Belfast Belfast United Kingdom

Diabetes, a pervasive and enduring health challenge, imposes significant global implications on health, financial healthcare systems, and societal well-being. This study undertakes a comprehensive exploration of various structural learning algorithms to discern causal pathways amongst potential risk factors influencing diabetes progression. The methodology involves the application of these algorithms to relevant diabetes data, followed by the conversion of their output graphs into Causal Bayesian Networks (CBNs), enabling predictive analysis and the evaluation of discrepancies in the effect of hypothetical interventions within our context-specific case study. This study highlights the substantial impact of algorithm selection on intervention outcomes. To consolidate insights from diverse algorithms, we employ a model-averaging technique that helps us obtain a unique causal model for diabetes derived from a varied set of structural learning algorithms. We also investigate how each of those individual graphs, as well as the average graph, compare to the structures elicited by a domain expert who categorised graph edges into high confidence, moderate, and low confidence types, leading into three individual graphs corresponding to the three levels of confidence. The resulting causal model and data are made available online, and serve as a valuable resource and a guide for informed decision-making by healthcare practitioners, offering a comprehensive understanding of the interactions between relevant risk factors and the effect of hypothetical interventions. Therefore, this research not only contributes to the academic discussion on diabetes, but also provides practical guidance for healthcare professionals in developing efficient intervention and risk management strategies. Copyright © 2024, The Authors. All rights reserved.

关键词： learning algorithms

When will generative adversarial imitation learning algorithms attain global convergence

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guan, Ziwei Xu, Tengyu Liang, Yingbin Department of Electrical and Computer Engineering Ohio State University

Generative adversarial imitation learning (GAIL) is a popular inverse reinforcement learning approach for jointly optimizing policy and reward from expert trajectories. A primary question about GAIL is whether applying a certain policy gradient algorithm to GAIL attains a global minimizer (i.e., yields the expert policy), for which existing understanding is very limited. Such global convergence has been shown only for the linear (or linear-type) MDP and linear (or linearizable) reward. In this paper, we study GAIL under general MDP and for nonlinear reward function classes (as long as the objective function is strongly concave with respect to the reward parameter). We characterize the global convergence with a sublinear rate for a broad range of commonly used policy gradient algorithms, all of which are implemented in an alternating manner with stochastic gradient ascent for reward update, including projected policy gradient (PPG)-GAIL, Frank-Wolfe policy gradient (FWPG)-GAIL, trust region policy optimization (TRPO)-GAIL and natural policy gradient (NPG)-GAIL. This is the first systematic theoretical study of GAIL for global convergence. Copyright © 2020, The Authors. All rights reserved.

关键词： learning algorithms

learning-based algorithms in scheduling

学校读者我要写书评

暂无评论

JOURNAL OF INTELLIGENT MANUFACTURING 2000年第2期11卷 135-143页

作者： Dudek-Dyduch, E AGH Univ Sci & Technol Inst Automat PL-30059 Krakow Poland

The aim of the paper is to present a conception of intelligent learning-based algorithms for scheduling. A general knowledge based model of a vast class of discrete deterministic processes is given. The model is a basis for the method of the synthesis of intelligent, learning-based algorithms, that is described in the paper. The designing simulation experiments that use learning is also described. To illustrate the presented ideas, the scheduling algorithm for a special NP-hard problem is given. The significant feature of the problem is that the retooling time depends not only on a pair of jobs to be processed directly one after the other, but also on the subset of jobs already performed. The proof of the NP-hardness of the problem is also given in the paper.

关键词： learning algorithms heuristics manufacturing discrete process processes state graph algebraic-logical model

Variational learning algorithms For Channel Estimation in RIS-assisted mmWave Systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nakul, Milind Rajoriya, Anupama Budhiraja, Rohit

We consider the problem of estimating the channel in reconfigurable intelligent surface (RIS) assisted millimeter wave (mmWave) systems. We propose two variational expectation maximization (VEM) based algorithms for channel estimation in RIS-aided wireless systems. The first algorithm is a structured mean field based sparse Bayesian learning (SM-SBL) algorithm that exploits the doubly-structured sparsity as well as the individual sparsity of the elements of the channel. To exploit the sparsities we propose a column-wise coupled Gaussian prior. We next design the factorized mean field based algorithm based on the prior we propose. This algorithm called the factorized mean field SBL (FM-SBL) algorithm addresses the time complexities of the SM-SBL algorithm without sacrificing channel estimation accuracy. We show using extensive numerical investigations that the i) proposed SM-SBL and FM-SBL algorithms outperform several existing algorithms and ii) FM-SBL has lower time complexity compared to the SM-SBL algorithm. © 2022, CC BY.

关键词： learning algorithms

Automated detection of polyps in CT colonography images using deep learning algorithms in colon cancer diagnosis

学校读者我要写书评

暂无评论

Automated detection of polyps in CT colonography images usin...

2017 International Conference on Energy, Communication, Data Analytics and Soft Computing, ICECDS 2017

作者： Godkhindi, Akshay M Gowda, Rajaram M. Department of Information Science and Engineering Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9781538618868

Colon cancer is cancer that is present on the inner side of colon walls or the rectum walls in the large intestine. Most of these types of cancer begin as abnormal growth of tissue called as polyp. Colonography uses low dose radiation Computed tomography (CT) scanning to obtain an interior view of the colon making use of special x-ray machine to view the large intestine for cancer and abnormal growths known as polyps. Radiologists examine these images to find polyp like structure using computer tools. As CT Colonography image contain noise such as lungs, small intestine, instruments during image capturing;segmenting colon from noise is the key task. Polyp occurrence can be detected mainly using shape feature;eliminating shapes similar to polyp is challenging. Hence, to tackle above issues, Image processing techniques are used by applying deep learning algorithm - Convolution Neural Network (CNN) and the results are compared with classical machine learning algorithm. In proposed method, each image is pre-processed to filter air filled dark region that includes colon, lungs etc. Next, each pre-processed CT Image separated into fixed number of blocks. Using pre-trained CNN, each block of ROI is classified as Type 1 (Usually Ascending and descending colon), Type 2 (Usually Traversal and sigmoidal colon) and Type3 (Noise such as lungs, instruments) to segment colon blocks by eliminating noise. Classified Blocks is further diagnosed for polyp like structure using pre-trained CNN by classifying each colon block as normal or abnormal. The experiment is setup with classical machine learning algorithms - Random Forest (RF) and k-nearest neighbor (KNN) by extracting texture feature - Local binary pattern (LBP) and shape feature - Histogram oriented gradient (HOG) for comparison. The experiment results showed the accuracy of proposed method for colon segmentation using CNN (87%) outperforms RF (85%) and KNN (83%). In, addition, the polyp detection accuracy of CNN (88%) is bette

关键词： learning algorithms