中文
相关论文

相关论文: Random Matrix Theory Proves that Deep Learning Rep…

200 篇论文

In this work we demonstrate that generative adversarial networks (GANs) can be used to generate realistic pervasive changes in remote sensing imagery, even in an unpaired training setting. We investigate some transformation quality metrics…

图像与视频处理 · 电气工程与系统科学 2020-05-19 Christopher X. Ren , Amanda Ziemann , James Theiler , Alice M. S. Durieux

We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data. Graphical-GAN conjoins the power of Bayesian networks on compactly representing the dependency structures among random variables and that of…

机器学习 · 计算机科学 2018-12-18 Chongxuan Li , Max Welling , Jun Zhu , Bo Zhang

This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the curse of dimensionality and allow for a compact…

机器学习 · 计算机科学 2022-02-21 Adam Celarek , Pedro Hermosilla , Bernhard Kerbl , Timo Ropinski , Michael Wimmer

Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been shown that a wide range of images can be projected into this…

计算机视觉与模式识别 · 计算机科学 2020-09-15 Jonas Wulff , Antonio Torralba

Generative adversarial networks (GANs) are a method based on the training of two neural networks, one called generator and the other discriminator, competing with each other to generate new instances that resemble those of the probability…

人工智能 · 计算机科学 2023-02-21 Jordi de la Torre

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution,…

计算机视觉与模式识别 · 计算机科学 2018-02-16 Antonia Creswell , Anil A Bharath

Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation. The fundamental principle of GANs is to approximate the…

机器学习 · 统计学 2018-03-22 G. Biau , B. Cadre , M. Sangnier , U. Tanielian

Generative Adversarial Networks (GANs) have proven to be a powerful framework for learning to draw samples from complex distributions. However, GANs are also notoriously difficult to train, with mode collapse and oscillations a common…

机器学习 · 统计学 2018-11-28 Kevin J Liang , Chunyuan Li , Guoyin Wang , Lawrence Carin

Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models…

机器学习 · 统计学 2016-06-03 Sebastian Nowozin , Botond Cseke , Ryota Tomioka

Generative adversarial networks (GAN) are a class of powerful machine learning techniques, where both a generative and discriminative model are trained simultaneously. GANs have been used, for example, to successfully generate "deep fake"…

密码学与安全 · 计算机科学 2021-07-06 Rakesh Nagaraju , Mark Stamp

Supervised learning, while deployed in real-life scenarios, often encounters instances of unknown classes. Conventional algorithms for training a supervised learning model do not provide an option to detect such instances, so they…

机器学习 · 计算机科学 2021-07-06 Jun Zhuang , Mohammad Al Hasan

As an entirely-new paradigm to design the communication systems, deep learning (DL), an approach that the machine learns the desired wireless function, has received much attention recently. In order to fully realize the benefit of DL-aided…

信息论 · 计算机科学 2024-05-14 Jinhong Kim , Yongjun Ahn , Byonghyo Shim

Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution…

In this paper, we present a deep-learning method to filter out effects such as ambient noise, reflections, or source directivity from microphone array data represented as cross-spectral matrices. Specifically, we focus on a generative…

声音 · 计算机科学 2025-03-03 Christof Puhle

With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the limited amount of labeled data available, supervised learning…

计算机视觉与模式识别 · 计算机科学 2017-11-22 Daoyu Lin , Kun Fu , Yang Wang , Guangluan Xu , Xian Sun

The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results…

机器学习 · 计算机科学 2017-04-05 Jeff Donahue , Philipp Krähenbühl , Trevor Darrell

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs. Recently different attacks and strategies have been proposed, but how to generate adversarial examples…

机器学习 · 计算机科学 2021-01-13 Tao Bai , Jun Zhao , Jinlin Zhu , Shoudong Han , Jiefeng Chen , Bo Li , Alex Kot

Generative adversarial networks (GANs) are widely used for distribution learning, yet their classical formulations remain theoretically fragile, with ill-posed objectives, unstable training dynamics, and limited interpretability. In this…

机器学习 · 计算机科学 2025-12-29 Angshul Majumdar

We introduce the Probabilistic Generative Adversarial Network (PGAN), a new GAN variant based on a new kind of objective function. The central idea is to integrate a probabilistic model (a Gaussian Mixture Model, in our case) into the GAN…

机器学习 · 计算机科学 2017-08-08 Hamid Eghbal-zadeh , Gerhard Widmer

Generative Adversarial Networks (GANs) are a revolutionary class of Deep Neural Networks (DNNs) that have been successfully used to generate realistic images, music, text, and other data. However, GAN training presents many challenges,…

机器学习 · 计算机科学 2022-03-30 Vineel Nagisetty , Laura Graves , Joseph Scott , Vijay Ganesh