检索结果-内蒙古大学图书馆

Unsupervised deep learning techniques for powdery mildew recognition based on multispectral imaging

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Benfenati, Alessandro Causin, Paola Oberti, Roberto Stefanello, Giovanni Dept. of Environmental Science and Policy Università degli Studi di Milano Milano Italy Dept. of Mathematics Università degli Studi di Milano Milano Italy Dept. of Agricultural and Environmental Sciences - Production Landscape Agroenergy Università degli Studi di Milano Milano Italy

Objectives: Sustainable management of plant diseases is an open challenge which has relevant economic and environmental impact. Optimal strategies rely on human expertise for field scouting under favourable conditions to assess the current presence and extent of disease symptoms. This labor-intensive task is complicated by the large field area to be scouted, combined with the millimeter-scale size of the early symptoms to be detected. In view of this, image-based detection of early disease symptoms is an attractive approach to automate this process, enabling a potential high throughput monitoring at sustainable costs. Methods: Deep learning has been successfully applied in various domains to obtain an automatic selection of the relevant image features by learning filters via a training procedure. Deep learning has recently entered also the domain of plant disease detection: following this idea, in this work we present a deep learning approach to automatically recognize powdery mildew on cucumber leaves. We focus on unsupervised deep learning techniques applied to multispectral imaging data and we propose the use of autoencoder architectures to investigate two strategies for disease detection: i) clusterization of features in a compressed space;ii) anomaly detection. Results. The two proposed approaches have been assessed by quantitative indices. The clusterization approach is not fully capable by itself to provide accurate predictions but it does cater relevant information. Anomaly detection has instead a significant potential of resolution which could be further exploited as a prior for supervised architectures with a very limited number of labeled samples. © 2021, CC BY.

关键词： learning algorithms

Using machine learning to select high-quality measurements

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Edmonds, Andrew Brown, David Vinas, Luciano Pagan, Samantha Lawrence Berkeley National Laboratory BerkeleyCA94720 United States University of California BerkeleyCA94720 United States University of North Carolina Chapel HillNC27514 United States

We describe the use of machine learning algorithms to select high-quality measurements for the Mu2e experiment. This technique is important for experiments with backgrounds that arise due to measurement errors. The algorithms use multiple pieces of ancillary information that are sensitive to measurement quality to separate high-quality and low-quality measurements. © 2021, CC BY-NC-SA.

关键词： learning algorithms

Multi-Task Federated Reinforcement learning with Adversaries

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Anwar, Aqeel Raychowdhury, Arijit Department of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement learning and propose an adaptive attack method with better attack performance. Furthermore, we modify the conventional federated reinforcement learning algorithm to address the issue of adversaries that works equally well with and without the adversaries. Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents. © 2021, CC BY.

关键词： learning algorithms

INTERPRETING EMERGENT PLANNING IN MODEL-FREE REINFORCEMENT learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bush, Thomas Chung, Stephen Anwar, Usman Garriga-Alonso, Adrià Krueger, David University of Cambridge United Kingdom FAR AI Mila University of Montreal Canada

We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban – a commonly used benchmark for studying planning. Specifically, we demonstrate that DRC, a generic model-free agent introduced by Guez et al. (2019), uses learned concept representations to internally formulate plans that both predict the long-term effects of actions on the environment and influence action selection. Our methodology involves: (1) probing for planning-relevant concepts, (2) investigating plan formation within the agent’s representations, and (3) verifying that discovered plans (in the agent’s representations) have a causal effect on the agent’s behavior through interventions. We also show that the emergence of these plans coincides with the emergence of a planning-like property: the ability to benefit from additional test-time compute. Finally, we perform a qualitative analysis of the planning algorithm learned by the agent and discover a strong resemblance to parallelized bidirectional search. Our findings advance understanding of the internal mechanisms underlying planning behavior in agents, which is important given the recent trend of emergent planning and reasoning capabilities in LLMs through RL. © 2025, CC BY.

关键词： learning algorithms

RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Godon, Thibaud Plante, Pier-Luc Bauvin, Baptiste Francovic-Fontaine, Élina Drouin, Alexandre Corbeil, Jacques Department of Computer Science and Software Université Laval Canada Department of Molecular Medicine Université Laval Canada Element Ai A ServiceNow Company

Background: Understanding the relationship between the Omics and the phenotype is a central problem in precision medicine. The high dimensionality of metabolomics data challenges learning algorithms in terms of scalability and generalization. Most learning algorithms do not produce interpretable models - Method: We propose an ensemble learning algorithm based on conjunctions or disjunctions of decision rules. - Results : Applications on metabolomics data shows that it produces models that achieves high predictive performances. The interpretability of the models makes them useful for biomarker discovery and patterns discovery in high dimensional data. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Fast Rate Generalization Error Bounds: Variations on a Theme

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Xuetong Manton, Jonathan H. Aickelin, Uwe Zhu, Jingge Department of EEE University of Melbourne ParkvilleVIC Australia Department of CIS University of Melbourne ParkvilleVIC Australia

A recent line of works, initiated by [1] and [2], has shown that the generalization error of a learning algorithm can be upper bounded by information measures. In most of the relevant works, the convergence rate of the expected generalization error is in the form of O(√λ/n) where λ is some information-theoretic quantities such as the mutual information between the data sample and the learned hypothesis. However, such a learning rate is typically considered to be "slow", compared to a "fast rate" of O(1/n) in many learning scenarios. In this work, we first show that the square root does not necessarily imply a slow rate, and a fast rate (1/n) result can still be obtained using this bound under appropriate assumptions. Furthermore, we identify the key conditions needed for the fast rate generalization error, which we call the (η, c)-central condition. Under this condition, we give information-theoretic bounds on the generalization error and excess risk, with a convergence rate of O (λ/n) for specific learning algorithms such as empirical risk minimization. Finally, analytical examples are given to show the effectiveness of the bounds. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Breaking Fair Binary Classification with Optimal Flipping Attacks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jo, Changhun Sohn, Jy-Yong Lee, Kangwook University of Wisconsin-Madison United States

Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the minimum amount of data corruption required for a successful flipping attack. First, we find lower/upper bounds on this quantity and show that these bounds are tight when the target model is the unique unconstrained risk minimizer. Second, we propose a computationally efficient data poisoning attack algorithm that can compromise the performance of fair learning algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Adaptive Federated Minimax Optimization with Lower Complexities

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Feihu Wang, Xinrui Li, Junyi Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Department of Electrical and Computer Engineering University of Pittsburgh Pittsburgh United States

Federated learning is a popular distributed and privacy-preserving learning paradigm in machine learning. Recently, some federated learning algorithms have been proposed to solve the distributed minimax problems. However, these federated minimax algorithms still suffer from high gradient or communication complexity. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate these algorithms. To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve these distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrices. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our AdaFGDA algorithm obtains a lower gradient (i.e., stochastic first-order oracle, SFO) complexity of O (ϵ-3) with lower communication complexity of O (ϵ-2) in finding ϵ-stationary point of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms. © 2022, CC BY-NC-SA.

关键词： learning algorithms

Revisiting dequantization and quantum advantage in learning tasks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cotler, Jordan Huang, Hsin-Yuan McClean, Jarrod R. Black Hole Initiative CambridgeMA02138 United States Institute for Quantum Information and Matter Caltech PasadenaCA United States Department of Computing and Mathematical Sciences Caltech PasadenaCA United States Google Quantum AI 340 Main Street VeniceCA90291 United States

It has been shown that the apparent advantage of some quantum machine learning algorithms may be efficiently replicated using classical algorithms with suitable data access - a process known as dequantization. Existing works on dequantization compare quantum algorithms which take copies of an n-qubit quantum state (Equation presented) as input to classical algorithms which have sample and query (SQ) access to the vector x. In this note, we prove that classical algorithms with SQ access can accomplish some learning tasks exponentially faster than quantum algorithms with quantum state inputs. Because classical algorithms are a subset of quantum algorithms, this demonstrates that SQ access can sometimes be significantly more powerful than quantum state inputs. Our findings suggest that the absence of exponential quantum advantage in some learning tasks may be due to SQ access being too powerful relative to quantum state inputs. If we compare quantum algorithms with quantum state inputs to classical algorithms with access to measurement data on quantum states, the landscape of quantum advantage can be dramatically different. © 2021, CC BY.

关键词： learning algorithms