首页>
外国专利>
Neural network learning method using auto encoder and multiple instance learning and computing system performing the same
Neural network learning method using auto encoder and multiple instance learning and computing system performing the same
展开▼
机译:使用自动编码器的神经网络学习方法以及执行该方法的多实例学习和计算系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
Disclosed are a method for learning a neural network with a small number of training data using an autoencoder and a multi-instance learning technique, and a computing system for performing the same. According to an aspect of the present invention, an autoencoder for determining whether an input data instance is in a first state or a second state, and a possibility that the input data instance is in a first state or a second state can be output. A method for learning a neural network performed in a computing system including a neural network, for each of a plurality of data bags labeled as either a first state or a second state, among data instances included in the data bag. An extraction step of extracting a part of the learning instance, and a learning step of learning the neural network based on the learning instance corresponding to each of the plurality of data bags, wherein the extraction step includes each data instance included in the data bag. Inputting into the neural network being learned, calculating a probability for each data instance included in the data bag, and at least some of the probability for each data instance included in the data bag, and each data instance included in the data bag There is provided a neural network training method including determining a part of each data instance included in the data bag as a training instance based on a determination result of the autoencoder for.
展开▼