More Like this

1. PMGAN: Paralleled Mix-Generator Generative Adversarial Networks with Balance Control

   Xiao, Xia ; Rajasekaran, Sanguthevar ( January 2018 , The 27th International Conference on Artificial Neural Networks)

   A Generative Adversarial Network (GAN) is an unsupervised generative framework to generate a sample distribution that is identical to the data distribution. Recently, mix strategy multi-generator/discriminator GANs have been shown to outperform single pair GANs. However, the mixed model suffers from the problem of linearly growing training time. Also, imbalanced training among generators makes it difficult to parallelize. In this paper, we propose a balanced mix-generator GAN that works in parallel by mixing multiple disjoint generators to approximate the real distribution. The weights of the discriminator and the classifier are controlled by a balance strategy. We also present an efficient loss function, to force each generator to embrace few modes with a high probability. Our model is naturally adaptive to large parallel computation frameworks. Each generator can be trained on multiple GPUs asynchronously. We have performed extensive experiments on synthetic datasets, MNIST1000, CIFAR-10, and ImageNet. The results establish that our model can achieve the state-of-the-art performance (in terms of the modes coverage and the inception score), with significantly reduced training time. We also show that the missing mode problem can be relieved with a growing number of generators. 

   more » « less
2. Condition Monitoring and Fault Diagnosis of Generators in Power Networks

   Yang, Bowen ; Li, Fangyu ; Ye, Jin ; Song, Wenzhan. ( August 2019 , IEEE Power & Energy Society General Meeting)

   In this paper, a novel hierarchical signal processing methodology is proposed for generator condition monitoring and fault diagnosis based on raw electrical waveform data in power networks, which can often be measured by strategically located waveform sensors. The impact of generator short circuit faults on strategically located electrical waveform sensors in power networks are firstly investigated and validated in Matlab Simulink. Based on the large set of electrical waveform data produced by Matlab Simulink, a hierarchical algorithm is then designed to locate fault site location and monitor the condition of generators in power networks. Finally, the proposed methodology is validated in 14-bus IEEE standard power network under different scenarios (e.g, one generator fault, two-generator-fault, various aging levels, etc). Our results show that we can locate fault site location and monitor the aging condition of generators in power networks. Compared to traditional condition monitoring and fault diagnosis based on generator sensors, our proposed methodology can monitor a large number of generators based on a limited number of waveform sensors, which promises to reduce the cost of the maintenance and improve the reliability of the power grid. 

   more » « less
3. Extending RC4 to construct secure random number generators

   Deng, L-Y. ( January 2021 , Proceedings of the 2021 Annual Modeling and Simulation Conference (ANNSIM '21). Society for Computer Simulation International)

   null (Ed.)

   We consider a general framework for constructing non-linear generators by adding a (32-bit or larger) pseudo-random number generator (PRNG) as a baseline generator to the basic RC4 design, in which an index-selection scheme similar to RC4 is used. We refer to the proposed design as the eRC (enhanced/ extended RC4) design. We discuss several advantages of adding a good baseline generator to the RC4 design, including new updating schemes for the auxiliary table. We consider some popular PRNGs with the nice properties of high-dimensional equi-distribution, efficiency, long period, and portability as the baseline generator. We demonstrate that eRC generators are very efficient via extensive empirical testing on some eRC generators. We also show that eRC is flexible enough to choose minimal design parameters for eRC generators and yet the resulting eRC generators still pass stringent empirical tests, which makes them suitable for both software and hardware implementations. 

   more » « less
4. On the Zero-Shot Generalization of Machine-Generated Text Detectors

   https://doi.org/10.18653/v1/2023.findings-emnlp.318  

   Pu, Xiao ; Zhang, Jingyu ; Han, Xiaochuang ; Tsvetkov, Yulia ; He, Tianxing ( January 2023 , Association for Computational Linguistics)

   The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of machine-generated text. This work is motivated by an important research question: How will the detectors of machine-generated text perform on outputs of a new generator, that the detectors were not trained on? We begin by collecting generation data from a wide range of LLMs, and train neural detectors on data from each generator and test its performance on held-out generators. While none of the detectors can generalize to all generators, we observe a consistent and interesting pattern that the detectors trained on data from a medium-size LLM can zero-shot generalize to the larger version. As a concrete application, we demonstrate that robust detectors can be built on an ensemble of training data from medium-sized models. 

   more » « less
5. General video game rule generation

   https://doi.org/10.1109/cig.2017.8080431  

   Khalifa, Ahmed ; Green, Michael Cerny ; Perez-Liebana, Diego ; Togelius, Julian ( August 2017 , 2017 IEEE Conference on Computational Intelligence and Games (CIG))

   We introduce the General Video Game Rule Gen- eration problem, and the eponymous software framework which will be used in a new track of the General Video Game AI (GVGAI) competition. The problem is, given a game level as input, to generate the rules of a game that fits that level. This can be seen as the inverse of the General Video Game Level Generation problem. Conceptualizing these two problems as separate helps breaking the very hard problem of generating complete games into smaller, more manageable subproblems. The proposed framework builds on the GVGAI software and thus asks the rule generator for rules defined in the Video Game Description Language. We describe the API, and three different rule generators: a random, a constructive and a search- based generator. Early results indicate that the constructive generator generates playable and somewhat interesting game rules but has a limited expressive range, whereas the search- based generator generates remarkably diverse rulesets, but with an uneven quality. 

   more » « less