相关论文: Adversarial Training Improves Joint Energy-Based G…

The robustness of neural networks to intended perturbations has recently attracted significant attention. In this paper, we propose a new method, \emph{learning with a strong adversary}, that learns robust classifiers from supervised data.…

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue. In this paper we…

Quantum machine learning is expected to be one of the first potential general-purpose applications of near-term quantum devices. A major recent breakthrough in classical machine learning is the notion of generative adversarial training,…

The field of adversarial robustness has attracted significant attention in machine learning. Contrary to the common approach of training models that are accurate in average case, it aims at training models that are accurate for worst case…

Generative adversarial networks (GANs) are a framework for producing a generative model by way of a two-player minimax game. In this paper, we propose the \emph{Generative Multi-Adversarial Network} (GMAN), a framework that extends GANs to…

We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both…

Model-based reinforcement learning has attracted much attention due to its high sample efficiency and is expected to be applied to real-world robotic applications. In the real world, as unobservable disturbances can lead to unexpected…

Most approaches to dense anomaly detection rely on generative modeling or on discriminative methods that train with negative data. We consider a recent hybrid method that optimizes the same shared representation according to cross-entropy…

Adversarial training is a technique of improving model performance by involving adversarial examples in the training process. In this paper, we investigate adversarial training with multiple adversarial examples to benefit the relation…

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs are typically trained end-to-end on real-valued data and can be used to train a generator of…

Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted…

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the…

In recent years, machine learning algorithms have been applied widely in various fields such as health, transportation, and the autonomous car. With the rapid developments of deep learning techniques, it is critical to take the security…

This report summarizes the tutorial presented by the author at NIPS 2016 on generative adversarial networks (GANs). The tutorial describes: (1) Why generative modeling is a topic worth studying, (2) how generative models work, and how GANs…

Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally…

As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose…

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes.…

This paper describes a method for using Generative Adversarial Networks to learn distributed representations of natural language documents. We propose a model that is based on the recently proposed Energy-Based GAN, but instead uses a…