论文标题
使用预训练和射击的几次学习，并富含预训练的样品
Few-shot learning using pre-training and shots, enriched by pre-trained samples
论文作者
论文摘要
我们使用手写数字的EMNIST数据集来测试一种简单的方法，以进行几次学习。完全连接的神经网络已通过10位数字的子集进行预训练，并用于未经训练的数字进行几次学习。引入了两个基本想法：在几次学习期间，学习第一层的学习是禁用的，并且对于每次镜头，先前未知的数字都将与四个先前训练的数字一起使用，直到满足预定义的阈值条件为止。这样，我们在10张照片后达到了约90％的精度。
We use the EMNIST dataset of handwritten digits to test a simple approach for few-shot learning. A fully connected neural network is pre-trained with a subset of the 10 digits and used for few-shot learning with untrained digits. Two basic ideas are introduced: during few-shot learning the learning of the first layer is disabled, and for every shot a previously unknown digit is used together with four previously trained digits for the gradient descend, until a predefined threshold condition is fulfilled. This way we reach about 90% accuracy after 10 shots.
