Machine learning has achieved remarkable success over the past couple of decades, often attributed to a combination of algorithmic innovations and the availability of high-quality data available at scale. However, a t...
详细信息
We merge the broadband, high resolution capabilities of dual frequency comb spectroscopy with a spatially resolving single pixel camera experimental architecture to demonstrate broadband spectroscopic imaging via comp...
详细信息
ISBN:
(数字)9781957171050
ISBN:
(纸本)9781665466660
We merge the broadband, high resolution capabilities of dual frequency comb spectroscopy with a spatially resolving single pixel camera experimental architecture to demonstrate broadband spectroscopic imaging via compressive sensing.
The complexity and heterogeneity of data in many real-world applications pose significant challenges for traditional machine learning and signal processing techniques. For instance, in medicine, effective analysis of ...
详细信息
Membership inference attack (MIA) has been proved to pose a serious threat to federated learning (FL). However, most of the existing membership inference attacks against FL rely on the specific attack models built fro...
Membership inference attack (MIA) has been proved to pose a serious threat to federated learning (FL). However, most of the existing membership inference attacks against FL rely on the specific attack models built from the target model behaviors, which make the attacks costly and complicated. In addition, directly adopting the inference attacks that are originally designed for machine learning models into the federated scenarios can lead to poor performance. We propose GBMIA, an attack model-free membership inference method based on gradient. We take full advantage of the federated learning process by observing the target model's behaviors after gradient ascent tuning. And we combine prediction correctness and the gradient norm-based metric for membership inference. The proposed GBMIA can be conducted by both global and local attackers. We conduct experimental evaluations on three real-world datasets to demonstrate that GBMIA can achieve a high attack accuracy. We further apply the arbitration mechanism to increase the effectiveness of GBMIA which can lead to an attack accuracy close to 1 on all three datasets. We also conduct experiments to substantiate that clients going offline and the overlap of clients' training sets have great effect on the membership leakage in FL.
Data in many applications follows systems of Ordinary Differential Equations (ODEs). This paper presents a novel algorithmic and symbolic construction for covariance functions of Gaussian Processes (GPs) with realizat...
ISBN:
(纸本)9781713871088
Data in many applications follows systems of Ordinary Differential Equations (ODEs). This paper presents a novel algorithmic and symbolic construction for covariance functions of Gaussian Processes (GPs) with realizations strictly following a system of linear homogeneous ODEs with constant coefficients, which we call LODE-GPs. Introducing this strong inductive bias into a GP improves modelling of such data. Using smith normal form algorithms, a symbolic technique, we overcome two current restrictions in the state of the art: (1) the need for certain uniqueness conditions in the set of solutions, typically assumed in classical ODE solvers and their probabilistic counterparts, and (2) the restriction to controllable systems, typically assumed when encoding differential equations in covariance functions. We show the effectiveness of LODE-GPs in a number of experiments, for example learning physically interpretable parameters by maximizing the likelihood.
In December 2018, the call for the Special Issue “Short-Term Load Forecasting 2019” of the journal Energies was launched. The submission deadline was in March 2020. The Special Issue followed in the footsteps of oth...
In December 2018, the call for the Special Issue “Short-Term Load Forecasting 2019” of the journal Energies was launched. The submission deadline was in March 2020. The Special Issue followed in the footsteps of other past Special Issues devoted to methods for energy demand forecasting. The call was well received, with 27 submissions of which 13 were published: 11 research articles and 2 review articles. Short-term load forecasting (STLF) has been a topic of interest for the journal Energies, with numerous articles published since its inception, and is one of the themes included in the open for submission multidisciplinary topics of MDPI. All the articles of the Special Issue were published in the MDPI book with the same title in February *** of interest for the call of the Special Issue included, but were not limited to:Short term load forecasting and distributed energy resourcesShort term load forecasting and demand aggregation levelsStatistical forecasting models (SARIMA, ARMAX, exponential smoothing, linear and non-linear regression, and so on)Artificial neural networks (ANNs)Fuzzy regression modelsTree-based regression methodsStacked and ensemble methodsEvolutionary algorithmsDeep learning architecturesSupport vector regression (SVR)Robust load forecastingHierarchical and probabilistic forecastingHybrid and combined modelsRegardless of the effort to develop increasingly accurate and reliable STLF methods, some of the aspects that, in our opinion, should be explored in the near future include the following:Distributed renewable energy generation, especially in local photovoltaic (PV), has grown intensively in recent years and, because of the current energy crisis, is expected to expand further in the near future. A high level of PV penetration in low- and medium-voltage grids can cause uncertainty in the operation and management processes carried out by utilities, because most meters register the net load, i.e., the difference between the actual load and
Image compression is an important topic in remote sensing applications such as in memory-constrained or low-bandwidth environments. An evaluation of a machine learning compression framework jointly paired with a super...
详细信息
ISBN:
(数字)9798350367621
ISBN:
(纸本)9798350367638
Image compression is an important topic in remote sensing applications such as in memory-constrained or low-bandwidth environments. An evaluation of a machine learning compression framework jointly paired with a super resolution network, to restore compressed images, is performed. Image quality and compression metrics are analyzed against existing techniques.
In a post-quantum world, where attackers may have access to full-scale quantum computers, all classical password-based authentication schemes will be compromised. Quantum copy-protection prevents adversaries from maki...
详细信息
Although the training of deep convolutional neural networks is usually accelerated by the use of high performance processors, their use on resource constrained devices is difficult. Several compression-based accelerat...
详细信息
Exceptional point (EP)-based optical sensors exhibit exceptional sensitivity but poor detectivity due to their acute sensitivity to perturbations such as noise. When the optical budget is limited as in applications on...
详细信息
暂无评论