检索结果-内蒙古大学图书馆

Applying Background learning algorithms to Radio Tomographic Imaging

学校读者我要写书评

暂无评论

Applying Background Learning Algorithms to Radio Tomographic...

16th International Symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Men, Aidong Xue, Jianfei Liu, Junyan Xu, Tianming Zheng, Yi Beijing Univ Posts & Telecommun Multimedia Technol Ctr Beijing Peoples R China

Radio tomographic imaging (RTI) is an emerging technique which obtains images of passive targets (i.e., not carrying electronic device) within a wireless sensor network using received signal strength (RSS). One major problem that restricts the application of RTI is the difficulty to model the variations of RSS measurements caused by moving targets in different multi-path environments. This paper proposes to apply background learning algorithm to RTI system to model variations. Compared with previous RSS-based device free localization methods, the proposed method achieves higher accuracy in multi-target and time-varying environment without offline training. Firstly, two fundamental background learning algorithms, mixture of gaussians and kernel density estimation, are introduced to calculate the probabilities of links being affected by targets using RSS measurement. Then, Tikhonov regularization is applied to the reconstruction of images using the probabilities. Experimental results show that the proposed approach achieves high accuracy and increases the RSS-network capacity considerably.

关键词： learning algorithms

Instance-dependent Label-noise learning under a Structural Causal Model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yao, Yu Liu, Tongliang Gong, Mingming Han, Bo Niu, Gang Zhang, Kun University of Sydney Australia University of Melbourne Australia Hong Kong Baptist University Hong Kong RIKEN AIP Japan Carnegie Mellon University United States

Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many datasets have been constructed, e.g., SVHN and CIFAR, the distributions of P(X) and P(Y |X) are entangled. This means that the unsupervised instances are helpful to learn the classifier and thus reduce the side effect of label noise. However, it remains elusive on how to exploit the causal information to handle the label noise problem. In this paper, by leveraging a structural causal model, we propose a novel generative approach for instance-dependent label-noise learning. In particular, we show that properly modelling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier. Empirically, our method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Towards Enabling Meta-learning from Target Models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lu, Su Ye, Han-Jia Gan, Le Zhan, De-Chuan State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Meta-learning can extract an inductive bias from previous learning experience and assist the training of new tasks. It is often realized through optimizing a meta-model with the evaluation loss of task-specific solvers. Most existing algorithms sample non-overlapping support sets and query sets to train and evaluate the solvers respectively due to simplicity (S/Q protocol). Different from S/Q protocol, we can also evaluate a task-specific solver by comparing it to a target model T , which is the optimal model for this task or a model that behaves well enough on this task (S/T protocol). Although being short of research, S/T protocol has unique advantages such as offering more informative supervision, but it is computationally expensive. This paper looks into this special evaluation method and takes a step towards putting it into practice. We find that with a small ratio of tasks armed with target models, classic meta-learning algorithms can be improved a lot without consuming many resources. We empirically verify the effectiveness of S/T protocol in a typical application of meta-learning, i.e., few-shot learning. In detail, after constructing target models by fine-tuning the pre-trained network on those hard tasks, we match the task-specific solvers and target models via knowledge distillation. © 2021, CC BY-NC-SA.

关键词： learning algorithms

Protaugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dopierre, Thomas Gravier, Christophe Logerais, Wilfried Laboratoire Hubert Curien UMR CNRS 5516 Université Jean Monnet Saint-Étienne France Meetic Paris France

Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose PROTAUGMENT, a meta-learning algorithm for short texts classification applied to the intent detection task. PROTAUGMENT is a novel extension of Prototypical Networks (Snell et al., 2017) that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data and then fueled to the Prototypical Network training objective as a consistency loss. PROTAUGMENT is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

learning with different amounts of annotation: From zero to many labels

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Shujian Gong, Chengyue Choi, Eunsol The University of Texas at Austin

Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that single label is not sufficient to learn the spectrum of language interpretation. We explore new annotation distribution schemes, assigning multiple labels per example for a small subset of training examples. Introducing such multi label examples at the cost of annotating fewer examples brings clear gains on natural language inference task and entity typing task, even when we simply first train with a single label data and then fine tune with multi label examples. Extending a MixUp data augmentation framework, we propose a learning algorithm that can learn from training examples with different amount of annotation (with zero, one, or multiple labels). This algorithm efficiently combines signals from uneven training data and brings additional gains in low annotation budget and cross domain settings. Together, our method achieves consistent gains in two tasks, suggesting distributing labels unevenly among training examples can be beneficial for many NLP tasks.1 © 2021, CC BY.

关键词： learning algorithms

Server-side local gradient averaging and learning rate acceleration for scalable split learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pal, Shraman Uniyal, Mansi Park, Jihong Vepakomma, Praneeth Raskar, Ramesh Bennis, Mehdi Jeon, Moongu Choi, Jinho IIT Kharagpur India Deakin University Australia MIT Media Lab United States GIST Korea Republic of University of Oulu Finland

In recent years, there have been great advances in the field of decentralized learning with private data. Federated learning (FL) and split learning (SL) are two spearheads possessing their pros and cons, and are suited for many user clients and large models, respectively. To enjoy both benefits, hybrid approaches such as SplitFed have emerged of late, yet their fundamentals have still been illusive. In this work, we first identify the fundamental bottlenecks of SL, and thereby propose a scalable SL framework, coined SGLR. The server under SGLR broadcasts a common gradient averaged at the split-layer, emulating FL without any additional communication across clients as opposed to SplitFed. Meanwhile, SGLR splits the learning rate into its server-side and client-side rates, and separately adjusts them to support many clients in parallel. Simulation results corroborate that SGLR achieves higher accuracy than other baseline SL methods including SplitFed, which is even on par with FL consuming higher energy and communication costs. As a secondary result, we observe greater reduction in leakage of sensitive information via mutual information using SLGR over the baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Sliding mode control for systems with mismatched time-varying uncertainties via a self-learning disturbance observer

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kayacan, Erkan Senseable City Laboratory Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States

This paper presents a novel Sliding Mode Control (SMC) algorithm to handle mismatched uncertainties in systems via a novel Self-learning Disturbance Observer (SLDO). A computationally efficient SLDO is developed within a framework of feedback-error learning scheme in which a conventional estimation law and a Neuro-Fuzzy Structure (NFS) work in parallel. In this framework, the NFS estimates the mismatched disturbances and becomes the leading disturbance estimator while the former feeds the learning error to the NFS to learn system behavior. The simulation results demonstrate that the proposed SMC based on SLDO (SMC-SLDO) ensures the robust control performance in the presence of mismatched time-varying uncertainties when compared to SMC, integral SMC (ISMC) and SMC based on a Basic Nonlinear Disturbance Observer (SMC-BNDO), and also remains the nominal control performance in the absence of mismatched uncertainties. Additionally, the SMC-SLDO not only counteracts mismatched time-varying uncertainties but also improve the transient response performance in the presence of mismatched time-invariant uncertainties. Moreover, the controller gain of the SMC-SLDO is required to be selected larger than the upper bound of the disturbance estimation error rather than the upper bound of the actual disturbance to guarantee the system stability which results in eliminating the chattering effects on the control signal. © 2021, CC BY.

关键词： learning algorithms

Put CASH on Bandits: A Max K-Armed Problem for Automated Machine learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Balef, Amir Rezaei Vernade, Claire Eggensperger, Katharina Department of Computer Science University of Tübingen Germany

The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max k-armed bandit method to trade off exploring different model classes and conducting hyperparameter optimization. MaxUCB is specifically designed for the light-tailed and bounded reward distributions arising in this setting and, thus, provides an efficient alternative compared to classic max k-armed bandit methods assuming heavy-tailed reward distributions. We theoretically and empirically evaluate our method on four standard AutoML benchmarks, demonstrating superior performance over prior approaches. Copyright © 2025, The Authors. All rights reserved.

关键词： learning algorithms

CTSKETCH: COMPOSITIONAL TENSOR SKETCHING FOR SCALABLE NEUROSYMBOLIC learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Choi, Seewon Solko-Breslin, Alaia Alur, Rajeev Wong, Eric University of Pennsylvania United States

Many computational tasks benefit from being formulated as the composition of neural networks followed by a discrete symbolic program. The goal of neurosymbolic learning is to train the neural networks using only end-to-end input-output labels of the composite. We introduce CTSketch, a novel, scalable neurosymbolic learning algorithm. CTSketch uses two techniques to improve the scalability of neurosymbolic inference: decompose the symbolic program into sub-programs and summarize each sub-program with a sketched tensor. This strategy allows us to approximate the output distribution of the program with simple tensor operations over the input distributions and summaries. We provide theoretical insight into the maximum error of the approximation. Furthermore, we evaluate CTSketch on many benchmarks from the neurosymbolic literature, including some designed for evaluating scalability. Our results show that CTSketch pushes neurosymbolic learning to new scales that have previously been unattainable by obtaining high accuracy on tasks involving over one thousand inputs. 1 © 2025, CC BY.

关键词： learning algorithms