Universal Language Model Fine-tuning for Text Classification Jeremy Howard∗ fast.ai University of San Francisco

First Page		Document Content
Date: 2018-05-23 20:17:13 Machine learning Artificial intelligence Computational neuroscience Learning Applied mathematics Artificial neural networks Cybernetics Formal sciences Deep learning Convolutional neural network Multi-task learning Training test and validation sets		Universal Language Model Fine-tuning for Text Classification Jeremy Howard∗ fast.ai University of San Francisco Add to Reading List Source URL: arxiv.org Download Document from Source Website File Size: 956,46 KB Share Document on Facebook

	SCAN 2018 Post-conference Proceedings Special Issue of Journal of Computational and Applied Mathematics Call for Papers Special Issue on the 18th International Symposium on Scientific Computing, Computer Arithmetic, DocID: 1xVSx - View Document
	Performance Evaluation and Optimization Models for Processing Networks with Queue-Dependent Production Quantities by John S. Hollywood S.B. Applied Mathematics DocID: 1xVdz - View Document
	Mixture Density Networks Christopher M. Bishop Neural Computing Research Group Dept. of Computer Science and Applied Mathematics Aston University DocID: 1xUJf - View Document
	Mathematics_BS_Applied.pdf DocID: 1xTYO - View Document
	A BOOTSTRAP INTERVAL ESTIMATOR FOR BAYES’ CLASSIFICATION ERROR Chad M. Hawes and Carey E. Priebe Johns Hopkins University Department of Applied Mathematics and Statistics Baltimore, MDABSTRACT DocID: 1vrMQ - View Document