共查询到20条相似文献，搜索用时 15 毫秒
1.
This paper presents the network bending framework, a new approach for manipulating and interacting with deep generative models. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during inference. In addition, we present a novel algorithm for analysing the deep generative model and clustering features based on their spatial activation maps. This allows features to be grouped together based on spatial similarity in an unsupervised fashion. This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant features of the generated results. We outline this framework, demonstrating our results on deep generative models for both image and audio domains. We show how it allows for the direct manipulation of semantically meaningful aspects of the generative process as well as allowing for a broad range of expressive outcomes. 相似文献
2.
Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations on the Labeled Faces in the Wild (LFW) dataset. The purpose of our research is to increase the size of the training dataset using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training dataset, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. The face generation method based on VAEs with perceptual loss can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets. 相似文献
3.
Density estimation, compression, and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE), which utilizes deterministic and discrete transformations of data. This class of models allows both conditional and unconditional sampling while simplifying the objective function. First, we use a single self-supervised transformation as a latent variable, where the transformation is either downscaling or edge detection. Next, we consider a hierarchical architecture, i.e., multiple transformations, and we show its benefits compared to the VAE. The flexibility of selfVAE in data reconstruction finds a particularly interesting use case in data compression tasks, where we can trade-off memory for better data quality and vice-versa. We present the performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA). 相似文献
4.
Convolutional neural networks have greatly improved the performance of image super-resolution. However, perceptual networks have problems such as blurred line structures and a lack of high-frequency information when reconstructing image textures. To mitigate these issues, a generative adversarial network based on multiscale asynchronous learning is proposed in this paper, whereby a pyramid structure is employed in the network model to integrate high-frequency information at different scales. Our scheme employs a U-net as a discriminator to focus on the consistency of adjacent pixels in the input image and uses the LPIPS loss for perceptual extreme super-resolution with stronger supervision. Experiments on benchmark datasets and independent datasets Set5, Set14, BSD100, and SunHays80 show that our approach is effective in restoring detailed texture information from low-resolution images. 相似文献
5.
Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with reduced dimensionality but preserves maximum information) and the Decoder (which reconstructs the input data from the compressed latent space). Autoencoders have found wide applications in dimensionality reduction, object detection, image classification, and image denoising applications. Variational Autoencoders (VAEs) can be regarded as enhanced Autoencoders where a Bayesian approach is used to learn the probability distribution of the input data. VAEs have found wide applications in generating data for speech, images, and text. In this paper, we present a general comprehensive overview of variational autoencoders. We discuss problems with the VAEs and present several variants of the VAEs that attempt to provide solutions to the problems. We present applications of variational autoencoders for finance (a new and emerging field of application), speech/audio source separation, and biosignal applications. Experimental results are presented for an example of speech source separation to illustrate the powerful application of variants of VAE: VAE, -VAE, and ITL-AE. We conclude the paper with a summary, and we identify possible areas of research in improving performance of VAEs in particular and deep generative models in general, of which VAEs and generative adversarial networks (GANs) are examples. 相似文献
6.
Probabilistic predictions with machine learning are important in many applications. These are commonly done with Bayesian learning algorithms. However, Bayesian learning methods are computationally expensive in comparison with non-Bayesian methods. Furthermore, the data used to train these algorithms are often distributed over a large group of end devices. Federated learning can be applied in this setting in a communication-efficient and privacy-preserving manner but does not include predictive uncertainty. To represent predictive uncertainty in federated learning, our suggestion is to introduce uncertainty in the aggregation step of the algorithm by treating the set of local weights as a posterior distribution for the weights of the global model. We compare our approach to state-of-the-art Bayesian and non-Bayesian probabilistic learning algorithms. By applying proper scoring rules to evaluate the predictive distributions, we show that our approach can achieve similar performance as the benchmark would achieve in a non-distributed setting. 相似文献
7.
8.
Christopher Yeung Ryan Tsai Benjamin Pham Brian King Yusaku Kawagoe David Ho Julia Liang Mark W. Knight Aaswath P. Raman 《Advanced Optical Materials》2021,9(20):2100548
Understanding how nano- or micro-scale structures and material properties can be optimally configured to attain specific functionalities remains a fundamental challenge. Photonic metasurfaces, for instance, can be spectrally tuned through material choice and structural geometry to achieve unique optical responses. However, existing numerical design methods require prior identification of specific material−structure combinations, or device classes, as the starting point for optimization. As such, a unified solution that simultaneously optimizes across materials and geometries has yet to be realized. To overcome these challenges, a global deep learning-based inverse design framework is presented, where a conditional deep convolutional generative adversarial network is trained on colored images encoded with a range of material and structural parameters, including refractive index, plasma frequency, and geometric design. It is demonstrated that, in response to target absorption spectra, the network can identify an effective metasurface in terms of its class, materials properties, and overall shape. Furthermore, the model can arrive at multiple design variants with distinct materials and structures that present nearly identical absorption spectra. The proposed framework is thus an important step towards global photonics and materials design strategies that can identify combinations of device categories, material properties, and geometric parameters which algorithmically deliver a sought functionality. 相似文献
9.
高空电磁脉冲的早期分量幅值高、频谱宽、分布范围广,是高空核爆的电磁效应的重要组成部分。分析了国内外高空电磁脉冲早期分量仿真计算法的研究进展,并选取基于高频近似并考虑电子与电磁场自洽作用的EXEMP算法进行详细介绍,通过数值计算结果总结了高空电磁脉冲的时域波形和空间分布随场源当量、爆高等参数变化的规律,与IEC标准约定的波形时域和空间特征一致。针对HEMP计算中部分参数的不确定性,分析参数取值偏差和波动对电磁脉冲计算结果的影响,使用多项式混沌方法联合Sobol全局敏感度指标对其进行不确定量化,得到电磁脉冲关键值可能分布的上下界、分布的概率密度等信息,分析各参数在特定取值范围内对电磁脉冲特征参数的影响及联合影响。 相似文献
10.
Balloon-borne based solar unmanned aerial vehicle (short for BS-UAV) has been researched prevalently due to the promising application area of near-space (i.e., 20–100 km above the ground) and the advantages of taking off. However, BS-UAV encounters serious fault in its taking off phase. The fault in taking off hinders the development of BS-UAV and causes great loss to human property. Thus, timely diagnosing the running state of BS-UAV in taking off phase is of great importance. Unfortunately, due to lack of fault data in the taking off phase, timely diagnosing the running state becomes a key challenge. In this paper, we propose Ponder to diagnose the running state of BS-UAV in the taking off phase. The key idea of Ponder is to take full advantage of existing data and complement fault data first and then diagnose current states. First, we compress existing data into a low-dimensional space. Then, we cluster the low-dimensional data into normal and outlier clusters. Third, we generate fault data with different aggression at different clusters. Finally, we diagnose fault state for each sampling at the taking off phase. With three datasets collected on real-world flying at different times, we show that Ponder outperforms existing diagnosing methods. In addition, we demonstrate Ponder’s effectiveness over time. We also show the comparable overhead. 相似文献
11.
高空电磁脉冲（HEMP）可能造成广域基础设施的故障或损毁,考虑到经济原因,需要科学合理地评估其中关键电气电子设备在HEMP辐照下的易损性。将不确定性量化与设备效应评估相结合,总结出基于裕量与不确定性量化（QMU）的电气电子设备易损性评估方法及其工作流程,包括：筛选设备关键参数,通常为耦合通道电流、电压的范数;通过HEMP环境及其与设备耦合的数值仿真及不确定性量化,得到HEMP下设备关键参数的概率分布,作为设备的威胁水平;对工作状态下设备进行HEMP效应试验,通过统计推断得到设备效应阈值概率分布,作为设备在威胁下的强度;计算威胁水平与设备强度间的距离,量化设备关键参数的裕量及其不确定性,评估HEMP下的设备易损性。基于QMU的电气电子设备易损性评估方法还可为后续防护设计提供基础数据和评估方法。 相似文献
12.
Neural networks play a growing role in many scientific disciplines, including physics. Variational autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional latent space, which have a probabilistic interpretation. In particular, the so-called encoder network, the first part of the VAE, which maps its input onto a position in latent space, additionally provides uncertainty information in terms of variance around this position. In this work, an extension to the autoencoder architecture is introduced, the FisherNet. In this architecture, the latent space uncertainty is not generated using an additional information channel in the encoder but derived from the decoder by means of the Fisher information metric. This architecture has advantages from a theoretical point of view as it provides a direct uncertainty quantification derived from the model and also accounts for uncertainty cross-correlations. We can show experimentally that the FisherNet produces more accurate data reconstructions than a comparable VAE and its learning performance also apparently scales better with the number of latent space dimensions. 相似文献
13.
14.
针对关键参数测试样本数有限的情况下,概率理论、区间分析等方法在对输出靶压幅度进行不确定性定量评价时存在局限性和不合理性,将D-S理论引入到靶压幅度的不确定性量化中,根据小子样测试信息得出不确定性参数的基本信任分配,以信任函数和似然函数构造靶压幅度的上下界概率分布,并以Monte Carlo方法求解。实验和仿真得出了靶压幅度的近似概率分布、置信区间及期望值分布区间等信息,并表明：与传统的概率方法相比,该方法避免了根据小样本测试信息构造概率分布的难题;与区间分析方法相比,该方法可得到更丰富的信息。 相似文献
15.
通过含温有界原子模型,给出基于35种交换关联势形式,计算等离子体电子状态方程不确定度的方法.设计一种快速粗估不确定度的方法,并在TF模型中进行检验.以金为例,计算温度从1.0 eV~10 000.0 eV、密度为1.0、10.0、100.0 g·cm-3的电子总能量、压强、离化度的不确定度和拟真值.计算结果可为工程设计提供参考. 相似文献
16.
Thanks to the tractability of their likelihood, several deep generative models show promise for seemingly straightforward but important applications like anomaly detection, uncertainty estimation, and active learning. However, the likelihood values empirically attributed to anomalies conflict with the expectations these proposed applications suggest. In this paper, we take a closer look at the behavior of distribution densities through the lens of reparametrization and show that these quantities carry less meaningful information than previously thought, beyond estimation issues or the curse of dimensionality. We conclude that the use of these likelihoods for anomaly detection relies on strong and implicit hypotheses, and highlight the necessity of explicitly formulating these assumptions for reliable anomaly detection. 相似文献
17.
Deep learning models and graphics processing units have completely transformed the field of machine learning. Recurrent neural networks and long short-term memories have been successfully used to model and predict complex systems. However, these classic models do not perform sequential reasoning, a process that guides a task based on perception and memory. In recent years, attention mechanisms have emerged as a promising solution to these problems. In this review, we describe the key aspects of attention mechanisms and some relevant attention techniques and point out why they are a remarkable advance in machine learning. Then, we illustrate some important applications of these techniques in the modeling of complex systems. 相似文献
18.
Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model’s uncertainty is evaluated using point-prediction metrics, such as the negative log-likelihood (NLL), expected calibration error (ECE) or the Brier score on held-out data. Marginal coverage of prediction intervals or sets, a well-known concept in the statistical literature, is an intuitive alternative to these metrics but has yet to be systematically studied for many popular uncertainty quantification techniques for deep learning models. With marginal coverage and the complementary notion of the width of a prediction interval, downstream users of deployed machine learning models can better understand uncertainty quantification both on a global dataset level and on a per-sample basis. In this study, we provide the first large-scale evaluation of the empirical frequentist coverage properties of well-known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and reinforce coverage as an important metric in developing models for real-world applications. 相似文献
19.
In the last few decades, text mining has been used to extract knowledge from free texts. Applying neural networks and deep learning to natural language processing (NLP) tasks has led to many accomplishments for real-world language problems over the years. The developments of the last five years have resulted in techniques that have allowed for the practical application of transfer learning in NLP. The advances in the field have been substantial, and the milestone of outperforming human baseline performance based on the general language understanding evaluation has been achieved. This paper implements a targeted literature review to outline, describe, explain, and put into context the crucial techniques that helped achieve this milestone. The research presented here is a targeted review of neural language models that present vital steps towards a general language representation model. 相似文献
20.
Anna V. Kalyuzhnaya Nikolay O. Nikitin Alexander Hvatov Mikhail Maslyaev Mikhail Yachmenkov Alexander Boukhanovsky 《Entropy (Basel, Switzerland)》2021,23(1)
In this paper, we describe the concept of generative design approach applied to the automated evolutionary learning of mathematical models in a computationally efficient way. To formalize the problems of models’ design and co-design, the generalized formulation of the modeling workflow is proposed. A parallelized evolutionary learning approach for the identification of model structure is described for the equation-based model and composite machine learning models. Moreover, the involvement of the performance models in the design process is analyzed. A set of experiments with various models and computational resources is conducted to verify different aspects of the proposed approach. 相似文献