The integration of machinelearning (ML) into antenna optimization has revolutionized the design and enhancement of antenna systems. This paper provides an in-depth review of the latest advancements in antenna design ...
详细信息
We consider the problem of designing a robust classifier in the presence of an adversary who aims to degrade classification performance by elaborately falsifying the test instance. We propose a model-agnostic defense ...
详细信息
ISBN:
(纸本)9781728176055
We consider the problem of designing a robust classifier in the presence of an adversary who aims to degrade classification performance by elaborately falsifying the test instance. We propose a model-agnostic defense approach wherein the true class label of the falsified instance is inferred by analyzing its proximity to each class as measured based on class-conditional data distributions. We present a k-nearest neighbors type approach to perform a sample-based approximation of the aforementioned probabilistic proximity analysis. The proposed approach is evaluated on three different real-world datasets in a game-theoretic setting, in which the adversary is assumed to optimize the attack design against the employed defense approach. In the game-theoretic evaluation, the proposed defense approach significantly outperforms benchmarks in various attack scenarios, demonstrating its efficacy against optimally designed attacks.
This work is originated from the MLSP 2014 Classification Challenge which tries to automatically detect subjects with schizophrenia and schizo-affective disorder by analyzing multi-modal features derived from magnetic...
详细信息
ISBN:
(纸本)9781479999880
This work is originated from the MLSP 2014 Classification Challenge which tries to automatically detect subjects with schizophrenia and schizo-affective disorder by analyzing multi-modal features derived from magnetic resonance imaging (MRI) data. We employ Deep Neural Network (DNN)based multi-view representation learning for combining multi-modal features. The DNN-based multi-view models include deep canonical correlation analysis (DCCA) and deep canonically correlated auto-encoders (DCCAE). In addition, support vector machine with Gaussian kernel is used to conduct classification with the compact bottleneck features learned by the deep multi-view models. Our experiments on the dataset provided by the MLSP Classification Challenge show that bottleneck features learned via deep multi-view models obtain better results than the trimming features used in the baseline system in terms of the receiver operating characteristic (ROC) area under the curve (AUC).
Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, which forms the bedrock of modern machinelearning. In this work, we seek to balance the fact that attenuating step-size...
详细信息
Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, which forms the bedrock of modern machinelearning. In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster to a limiting error. To do so, rather than fixing the mini-batch and the step-size at the outset, we propose a strategy to allow parameters evolving adaptively. Specifically, the batch-size is set to be a piecewise-constant increasing sequence where the increase occurs when a suitable error criterion is satisfied. Moreover, the step-size is selected as that which yields the fastest convergence. The overall algorithm, two scale adaptive (TSA) scheme, is developed for both convex and non-convex problems. It inherits the exact convergence and more importantly, the optimal error decreasing rate and an overall computation reduction are achieved. Furthermore, we extended the TSA method to the generalized adaptive batching framework, which is a generic methodology modular to any stochastic algorithms pursuing a trade-off between convergence rates and stochastic variance. We evaluate the TSA method on the image classification problem on MNIST and CIFAR-10 datasets compared with standard SGD methods and existing adaptive batch-size methods, to corroborate theoretical findings.
Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for fe...
详细信息
ISBN:
(纸本)9781665405409
Non-intrusive load monitoring (NILM) is the analysis of electricity loads by means of a single supply wire, so avoiding separate monitors on individual appliances. Some approaches to NILM use the V-I trajectory for feature generation but they apply ad-hoc rules to generate the feature vector. This paper demonstrates a systematic method of feature generation called the path signature which has recently been applied in machinelearning, often with notable success. We show how the path signature generates features from the V-I trajectory to give a test set accuracy of 98.81% on the COOLL dataset. We conclude that the path signature is easier to use and generalize than ad-hoc features, and it can be applied to many other applications which use multivariate sequential data.
Selecting a learning criterion is a constituent part of a machinelearning problem statement requiring both accounting its adequacy to the data available and practical suitability of implementation. The paper presents...
详细信息
A novel method for online tracking of the changes in the nonlinearity within complex-valued signals is introduced. This is achieved by a collaborative adaptive signalprocessing approach by means of a hybrid filter. B...
详细信息
ISBN:
(纸本)9781424414833
A novel method for online tracking of the changes in the nonlinearity within complex-valued signals is introduced. This is achieved by a collaborative adaptive signalprocessing approach by means of a hybrid filter. By tracking the dynamics of the adaptive mixing parameter within the employed hybrid filtering architecture, we show that it is possible to quantify the degree of nonlinearity within complex-valued data. Simulations on both benchmark and real world data support the approach.
Deep learning (DL) based direction of arrival (DOA) estimation is an active research topic and currently represents the state-of-the-art. Usually, DL-based DOA estimators are trained with recorded data or computationa...
详细信息
ISBN:
(纸本)9781728176055
Deep learning (DL) based direction of arrival (DOA) estimation is an active research topic and currently represents the state-of-the-art. Usually, DL-based DOA estimators are trained with recorded data or computationally expensive generated data. Both data types require significant storage and excessive time to, respectively, record or generate. We propose a low complexity online data generation method to train DL models with a phase-based feature input. The data generation method models the phases of the microphone signals in the frequency domain by employing a deterministic model for the direct path and a statistical model for the late reverberation of the room transfer function. By an evaluation using data from measured room impulse responses, we demonstrate that a model trained with the proposed training data generation method performs comparably to models trained with data generated based on the source-image method.
The cost associated with manually labeling every individual instance in large datasets is prohibitive. Significant labeling efforts can be saved by assigning a collective label to a group of instances (a bag). This se...
详细信息
ISBN:
(纸本)9781479949755
The cost associated with manually labeling every individual instance in large datasets is prohibitive. Significant labeling efforts can be saved by assigning a collective label to a group of instances (a bag). This setup prompts the need for algorithms that allow labeling individual instances (instance annotation) based on bag-level labels. Probabilistic models in which instance-level labels are latent variables can be used for instance annotation. Brute-force computation of instance-level label probabilities is exponential in the number of instances per bag due to marginalization over all possible combinations. Existing solutions for addressing this issue include approximate methods such as sampling or variational inference. This paper proposes a discriminative probability model and an expectation maximization procedure for inference to address the instance annotation problem. A key contribution is a dynamic programming solution for exact computation of instance probabilities in quadratic time. Experiments on bird song, image annotation, and two synthetic datasets show a significant accuracy improvement by 4%-14% over a recent state-of-the-art rank loss SIM method.
Web attacks are one of the main threats to network information security, and these threats are also increasing. Firewalls and IDSs are signature-based security system devices, it is difficult for them to identify new ...
详细信息
ISBN:
(纸本)9780738105451
Web attacks are one of the main threats to network information security, and these threats are also increasing. Firewalls and IDSs are signature-based security system devices, it is difficult for them to identify new attack methods adopted by attackers, but honeypots can deal with this problem. Our honeypot is based on crawler technology, which have a well performance in deception. Traditional honeypots cannot help us eliminate some noise and useless data, because it does not have the ability to analyze data. This paper proposed a machinelearning enhanced honeypot to reduce the labor cost in data analysis and address this problem. In order to purify the attack data in the honeypot better, we present an ensemble algorithm called regret, which can be used to heterogeneous ensemble. This method could improve the detection performance.
暂无评论