首页> 外文会议>International Conference on Artificial Neural Networks >Increasing the Generalisaton Capacity of Conditional VAEs
【24h】

Increasing the Generalisaton Capacity of Conditional VAEs

机译:增加条件式VAE的通用能力

获取原文

摘要

We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost. The framework of conditional variational autoen-coders describes a class of methods to tackle such structured-prediction tasks by means of latent variables. We propose to incentivise informative latent representations for increasing the generalisation capacity of conditional variational autoencoders. To this end, we modify the latent variable model by defining the likelihood as a function of the latent variable only and introduce an expressive multimodal prior to enable the model for capturing semantically meaningful features of the data. To validate our approach, we train our model on the Cornell Robot Grasping dataset, and modified versions of MNIST and Fashion-MNIST obtaining results that show a significantly higher generalisation capability.
机译:我们解决了有监督学习中的一对多映射问题,其中单个实例具有成本可能相等的许多不同解决方案。条件变分自动编码器框架描述了一类通过潜在变量解决此类结构化预测任务的方法。我们建议激励信息性潜在表示,以提高条件变分自动编码器的泛化能力。为此,我们通过仅将可能性定义为潜在变量的函数来修改潜在变量模型,并在使模型能够捕获数据的语义上有意义的特征之前引入表达性多模态。为了验证我们的方法,我们在Cornell机器人抓取数据集上训练了模型,并使用MNIST和Fashion-MNIST的修改版获得了显示出明显更高泛化能力的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号